© 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 Local
    9. 6-RES_SCL-AJT
    11. 34828
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or appreciation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    151
    +0.12
    0.6%
    136
    +0.11
    0.5%
    254
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.12
    0.06
    23
    +0.11
    0.06
    12
    +0.09
    0.05
    Negative Logits
     deviation
    -0.64
     hardness
    -0.62
    itic
    -0.62
     projecting
    -0.61
    é¾įå¥ij士
    -0.60
    ãĤ¨ãĥ«
    -0.59
     Osc
    -0.59
     ["
    -0.58
     Luxem
    -0.58
    inese
    -0.57
    POSITIVE LOGITS
    gments
    0.77
    gements
    0.76
     Thank
    0.71
    Override
    0.68
    giving
    0.68
    ride
    0.65
    ribly
    0.65
    bles
    0.65
    ickets
    0.64
     recipients
    0.63
    Activations Density 2.793%

    No Known Activations