© 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
    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. 19
    Prev
    Next
    INDEX
    Explanations

    information related to the Tour de France

    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
    430
    +0.11
    0.6%
    153
    +0.10
    0.5%
    668
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    126
    +0.11
    0.03
    287
    +0.10
    0.03
    103
    +0.09
    0.04
    Negative Logits
    yip
    -0.78
    baugh
    -0.71
    ascript
    -0.61
    steen
    -0.60
    emort
    -0.59
    ible
    -0.59
    hemy
    -0.58
    blance
    -0.58
    imoto
    -0.58
    ierrez
    -0.57
    POSITIVE LOGITS
    Merit
    0.69
    ople
    0.54
    FORMATION
    0.54
     odds
    0.52
    Vision
    0.49
    bec
    0.48
    arts
    0.47
     Federation
    0.47
    OLOG
    0.46
    ucle
    0.46
    Activations Density 0.663%

    No Known Activations