© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 967
    Prev
    Next
    INDEX
    Explanations

    names or specific proper nouns

    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
    757
    +0.12
    0.5%
    210
    +0.12
    0.5%
    612
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.12
    0.07
    757
    +0.12
    0.05
    566
    +0.12
    0.06
    Negative Logits
    hap
    -0.91
     endif
    -0.83
    detail
    -0.77
    ivably
    -0.76
     Seah
    -0.73
     Vaughan
    -0.73
    verting
    -0.72
    kins
    -0.70
     RL
    -0.69
     Seat
    -0.67
    POSITIVE LOGITS
     wont
    0.94
    taboola
    0.88
     cant
    0.79
    pec
    0.76
    idem
    0.76
    emic
    0.75
    ´
    0.74
    erm
    0.74
    cius
    0.74
    enum
    0.73
    Activations Density 0.867%

    No Known Activations