© 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 12288
    9. 8-RES_FS12288-JB
    11. 359
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of events or situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    68
    +0.12
    0.6%
    29
    +0.11
    0.5%
    320
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.12
    0.03
    766
    +0.11
    0.03
    320
    +0.10
    0.02
    Negative Logits
    alde
    -0.65
    assi
    -0.63
    iasm
    -0.60
    ificial
    -0.59
    arent
    -0.59
     runoff
    -0.58
    ground
    -0.57
    fort
    -0.57
    umo
    -0.57
    onso
    -0.56
    POSITIVE LOGITS
     Patterns
    0.76
     descriptions
    0.75
     how
    0.71
     patterns
    0.69
    REDACTED
    0.69
     symptoms
    0.68
    urated
    0.66
    imens
    0.66
     traits
    0.66
    enance
    0.65
    Activations Density 0.096%

    No Known Activations