Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar L0 E2E Recon
    5. 2-RES_SLEFR-AJT
    6. 5445
    Prev
    Next
    INDEX
    Explanations

    The examples show the word "wheat" appearing in diverse contexts, including discussions of agricultural practices, food production, recipes, and even a video game bug report. The recurrence of "wheat" highlights its significance as a common agricultural crop and ingredient.

    eleuther_acts_top20 · gemini-1.5-flashTriggered by @johnny

    references to grains, particularly wheat and related crops

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_slefr-ajt/2-res_slefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    289
    +0.08
    0.5%
    433
    +0.07
    0.5%
    469
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.08
    0.01
    99
    +0.07
    0.01
    110
    +0.07
    0.01
    Negative Logits
    ĸļ
    -0.56
    nels
    -0.54
    ofi
    -0.53
     congr
    -0.52
    nova
    -0.50
    undo
    -0.50
    ntil
    -0.50
    CLASSIFIED
    -0.49
    alist
    -0.48
    utsche
    -0.48
    POSITIVE LOGITS
    MY
    0.51
    Lord
    0.50
    ׾
    0.49
     Coyotes
    0.47
    ×ŀ
    0.46
    Turkish
    0.46
    ãĥ¼ãĥ³
    0.46
     Grain
    0.45
    mega
    0.45
    iances
    0.45
    Activations Density 0.007%

    No Known Activations