© 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. 18511
    Prev
    Next
    INDEX
    Explanations

    references to the real world or physical locations

    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
    481
    +0.19
    0.9%
    423
    +0.12
    0.5%
    408
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    547
    +0.19
    0.05
    288
    +0.12
    0.06
    225
    +0.11
    0.06
    Negative Logits
    Lear
    -0.74
    ivas
    -0.73
    boa
    -0.72
    ãĤ±
    -0.70
    ãĥīãĥ©
    -0.63
    sbm
    -0.63
    lear
    -0.62
    cel
    -0.62
     pione
    -0.62
     Pop
    -0.62
    POSITIVE LOGITS
     onwards
    0.77
     itself
    0.73
     realm
    0.72
     aisle
    0.71
     onward
    0.70
    .(
    0.69
     sciences
    0.69
    SPONSORED
    0.68
    .
    0.67
    liest
    0.66
    Activations Density 0.278%

    No Known Activations