© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6426
    Prev
    Next
    INDEX
    Explanations

    comments and statements made by officials or sources

    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
    234
    +0.12
    0.5%
    760
    +0.11
    0.5%
    392
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    506
    +0.12
    0.04
    21
    +0.11
    0.04
    224
    +0.11
    0.04
    Negative Logits
    Population
    -0.72
     landfall
    -0.72
     vandalism
    -0.72
     prayers
    -0.70
    Interstitial
    -0.70
    TIT
    -0.68
    tumblr
    -0.68
    ãĥĺ
    -0.66
    Viol
    -0.65
     billboards
    -0.65
    POSITIVE LOGITS
     briefed
    1.21
     familiar
    1.00
     disclosed
    0.89
     quoted
    0.88
     knowledgeable
    0.87
    amiliar
    0.83
     told
    0.82
     insider
    0.81
     surn
    0.81
    idav
    0.80
    Activations Density 0.132%

    No Known Activations