© 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. 1752
    Prev
    Next
    INDEX
    Explanations

    names of specific spider species

    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
    677
    +0.10
    0.5%
    537
    +0.10
    0.4%
    674
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.10
    0.03
    284
    +0.10
    0.03
    134
    +0.10
    0.03
    Negative Logits
    sheet
    -0.80
     scoreboard
    -0.78
    efully
    -0.74
    handled
    -0.74
    ammy
    -0.73
    iless
    -0.72
    eful
    -0.70
     broadcasting
    -0.70
     referee
    -0.69
    writer
    -0.69
    POSITIVE LOGITS
    aceae
    1.60
    idae
    1.35
     genus
    1.21
     Species
    1.19
    opsis
    1.18
     species
    1.00
     coli
    0.97
    osaurus
    0.95
    illus
    0.94
    aurus
    0.92
    Activations Density 0.080%

    No Known Activations