© 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. 14127
    Prev
    Next
    INDEX
    Explanations

    apologies or expressions of regret

    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
    267
    +0.18
    0.6%
    236
    +0.16
    0.5%
    655
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    32
    +0.18
    0.03
    236
    +0.16
    0.03
    760
    +0.13
    0.03
    Negative Logits
    Ranked
    -1.19
    tnc
    -1.03
    arnaev
    -0.95
    irrel
    -0.95
    ieth
    -0.91
    icle
    -0.91
    krit
    -0.90
    sports
    -0.89
    edience
    -0.89
    buck
    -0.87
    POSITIVE LOGITS
     sorry
    1.31
     excuse
    1.29
    GES
    1.13
     excuses
    1.01
    tm
    1.00
    sorry
    0.99
    vm
    0.98
    Sorry
    0.94
     Customers
    0.92
    SQL
    0.91
    Activations Density 0.392%

    No Known Activations