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. 5393
    Prev
    Next
    INDEX
    Explanations

    references to "Community" or related terms indicating a focus on community initiatives and connections

    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
    608
    +0.10
    0.6%
    302
    +0.10
    0.6%
    622
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    515
    +0.10
    0.04
    508
    +0.10
    0.04
    444
    +0.08
    0.03
    Negative Logits
    gypt
    -0.62
    otomy
    -0.59
    gling
    -0.58
    opus
    -0.58
    mentation
    -0.56
    omen
    -0.56
    igible
    -0.56
    nesses
    -0.53
    agger
    -0.53
    inx
    -0.52
    POSITIVE LOGITS
     Community
    0.65
     dividend
    0.58
     Safety
    0.58
     cohesion
    0.55
     reinvest
    0.54
    iership
    0.53
    anooga
    0.53
     Associ
    0.52
     Register
    0.51
     rapport
    0.51
    Activations Density 0.084%

    No Known Activations