© 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. 7134
    Prev
    Next
    INDEX
    Explanations

    automotive terms related to repairs and modifications

    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
    365
    +0.12
    0.5%
    195
    +0.11
    0.5%
    26
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.12
    0.02
    220
    +0.11
    0.02
    26
    +0.11
    0.02
    Negative Logits
     Seym
    -1.02
    abad
    -0.74
     nomine
    -0.69
     Lumpur
    -0.68
    icipated
    -0.68
    uba
    -0.67
    ileaks
    -0.67
     suspic
    -0.66
    wealth
    -0.65
     Fernand
    -0.64
    POSITIVE LOGITS
    train
    1.03
    away
    0.87
    bys
    0.79
    wheel
    0.78
    back
    0.77
    Club
    0.76
    Drive
    0.76
    aways
    0.76
    club
    0.75
    HAM
    0.74
    Activations Density 0.024%

    No Known Activations