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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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 CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13961
    Prev
    Next
    INDEX
    Explanations

    actor and celebrity names, especially those named Kevin

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    659
    +0.14
    0.5%
    415
    +0.12
    0.4%
    525
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.07
    326
    +0.12
    0.09
    343
    +0.12
    0.07
    Negative Logits
    schild
    -1.09
    yrinth
    -1.01
    recomm
    -1.01
    pmwiki
    -0.93
    ¥µ
    -0.93
    atari
    -0.91
    ledged
    -0.91
    Ö¼
    -0.90
    MENTS
    -0.87
    bler
    -0.87
    POSITIVE LOGITS
     Rudd
    1.20
    arios
    1.13
     Durant
    1.08
     Harris
    1.06
     Dunn
    1.06
     Bacon
    1.04
    istic
    1.04
    essen
    1.03
    ists
    1.02
    aceous
    1.02
    Activations Density 1.725%

    No Known Activations