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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4101
    Prev
    Next
    INDEX
    Explanations

    phrases related to impossibility

    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
    736
    +0.13
    0.6%
    288
    +0.12
    0.6%
    718
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.13
    0.06
    119
    +0.12
    0.06
    408
    +0.12
    0.06
    Negative Logits
    erva
    -0.84
    ivities
    -0.82
    ript
    -0.81
    oche
    -0.80
    nan
    -0.75
    aina
    -0.75
    avia
    -0.74
    se
    -0.74
    oola
    -0.74
    iang
    -0.72
    POSITIVE LOGITS
    istically
    0.75
     feas
    0.73
     unanim
    0.71
     perfection
    0.69
     tampering
    0.68
     exists
    0.67
     Romeo
    0.67
     coincidence
    0.66
    ãĥ¬
    0.62
     simultane
    0.62
    Activations Density 0.921%

    No Known Activations