© 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. 210
    Prev
    Next
    INDEX
    Explanations

    technical terms related to industry or technology

    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
    36
    +0.16
    0.8%
    393
    +0.11
    0.5%
    362
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.16
    0.12
    362
    +0.11
    0.07
    328
    +0.11
    0.04
    Negative Logits
     boils
    -0.79
     impressions
    -0.77
    iments
    -0.74
     reactions
    -0.74
    loads
    -0.73
    words
    -0.70
     accusations
    -0.70
     shouts
    -0.69
     remarks
    -0.69
     cries
    -0.68
    POSITIVE LOGITS
     reputable
    1.22
     nearby
    1.02
     predetermined
    1.01
     specific
    0.95
     designated
    0.94
     local
    0.92
     trusted
    0.89
     particular
    0.88
     boutique
    0.85
     different
    0.85
    Activations Density 0.317%

    No Known Activations