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

    Neuronpedia

    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. 8141
    Prev
    Next
    INDEX
    Explanations

    economic terms and indicators

    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
    87
    +0.47
    2.6%
    756
    +0.21
    1.2%
    464
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.47
    -0.01
    756
    +0.21
    -0.01
    283
    +0.12
    0.01
    Negative Logits
    apeake
    -0.49
     Tsarnaev
    -0.48
    ?",
    -0.46
     Appalachian
    -0.46
     Pulitzer
    -0.45
     biologist
    -0.45
     Koch
    -0.44
     Bernstein
    -0.43
     PACs
    -0.43
     Predators
    -0.42
    POSITIVE LOGITS
    '.
    0.71
    .).
    0.70
    %.
    0.63
    `.
    0.63
    ".
    0.59
    +.
    0.59
    ().
    0.58
     onwards
    0.58
    ģ«
    0.55
    >.
    0.55
    Activations Density 1.815%

    No Known Activations