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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1373
    Prev
    Next
    INDEX
    Explanations

    news articles and reports on various topics

    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
    655
    +0.03
    0.5%
    245
    +0.03
    0.5%
    571
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    209
    +0.03
    0.03
    417
    +0.03
    0.02
    591
    +0.02
    0.02
    Negative Logits
    ategory
    -0.23
    hyde
    -0.21
    ttle
    -0.21
    plet
    -0.20
    ĸļ
    -0.20
    mary
    -0.19
    vati
    -0.19
    trl
    -0.19
    manship
    -0.18
     adjourn
    -0.18
    POSITIVE LOGITS
     LF
    0.19
     Syri
    0.17
    к
    0.17
    Ey
    0.17
     SY
    0.16
    audi
    0.16
    AZ
    0.16
     Corinth
    0.16
    598
    0.16
    Syrian
    0.16
    Activations Density 0.229%

    No Known Activations