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. 5414
    Prev
    Next
    INDEX
    Explanations

    mentions of "Zen" and related terms

    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
    659
    +0.12
    0.6%
    622
    +0.11
    0.6%
    715
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.01
    354
    +0.11
    0.01
    343
    +0.10
    0.01
    Negative Logits
    external
    -0.75
    riers
    -0.75
    Scotland
    -0.72
    riages
    -0.68
    女
    -0.67
    nl
    -0.64
    cutting
    -0.63
     Mulcair
    -0.63
    ãĥŀ
    -0.62
    instance
    -0.62
    POSITIVE LOGITS
    gard
    0.80
    geist
    0.70
     solution
    0.70
    hower
    0.66
     solutions
    0.64
     Zen
    0.63
    uner
    0.63
     kernels
    0.63
    ippery
    0.62
    inka
    0.62
    Activations Density 0.017%

    No Known Activations