© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 18914
    Prev
    Next
    INDEX
    Explanations

    quotes or reported statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    157
    +0.11
    0.5%
    679
    +0.10
    0.5%
    33
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.11
    0.04
    274
    +0.10
    0.04
    142
    +0.10
    0.04
    Negative Logits
     Himself
    -0.97
    artist
    -0.70
    amic
    -0.68
    OTUS
    -0.67
    Batman
    -0.66
    Insert
    -0.64
    ammy
    -0.63
     himself
    -0.63
    uper
    -0.61
    thia
    -0.61
    POSITIVE LOGITS
     they
    0.84
     alike
    0.73
     it
    0.62
     theirs
    0.61
     goodbye
    0.61
     there
    0.60
    selves
    0.60
     privately
    0.60
     Rising
    0.60
     delays
    0.59
    Activations Density 0.133%

    No Known Activations