© 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. 18338
    Prev
    Next
    INDEX
    Explanations

    statements or opinions

    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
    55
    +0.11
    0.5%
    395
    +0.10
    0.4%
    748
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.11
    0.07
    7
    +0.10
    0.04
    718
    +0.10
    0.05
    Negative Logits
    erk
    -0.63
     Chu
    -0.61
     Farming
    -0.61
     Thib
    -0.60
    igs
    -0.60
     Mons
    -0.59
    tz
    -0.59
     Bangl
    -0.58
    pheus
    -0.56
     Studies
    -0.56
    POSITIVE LOGITS
     consequently
    1.04
     accordingly
    0.97
     certainly
    0.95
     definitely
    0.91
     doubtless
    0.86
     nowhere
    0.83
     rewarded
    0.82
     thereafter
    0.81
     promptly
    0.81
     therefore
    0.81
    Activations Density 0.254%

    No Known Activations