© 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. 1228
    Prev
    Next
    INDEX
    Explanations

    references to specific software libraries or programming code snippets

    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
    28
    +0.07
    0.5%
    497
    +0.07
    0.4%
    331
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.07
    -0.01
    287
    +0.07
    0.01
    580
    +0.07
    0.01
    Negative Logits
    ourke
    -0.50
    chwitz
    -0.48
     Naj
    -0.47
    ainer
    -0.47
    ulkan
    -0.42
    rador
    -0.41
    ukong
    -0.41
    uko
    -0.41
     optionally
    -0.41
     emphas
    -0.41
    POSITIVE LOGITS
    NetMessage
    0.53
    scl
    0.47
    birth
    0.46
    mble
    0.45
    çľ
    0.43
    IGH
    0.43
    ãĥŁ
    0.42
    æł
    0.41
    ãĥł
    0.41
    ãĢĮ
    0.40
    Activations Density 0.048%

    No Known Activations