© 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. 24151
    Prev
    Next
    INDEX
    Explanations

    nouns and related actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    404
    +0.09
    0.4%
    432
    +0.09
    0.4%
    690
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    698
    +0.09
    0.02
    576
    +0.09
    0.01
    545
    +0.09
    0.02
    Negative Logits
    ien
    -0.78
    ographs
    -0.76
    ograph
    -0.76
    ibu
    -0.69
    asio
    -0.66
    inational
    -0.65
    umbs
    -0.64
     Rats
    -0.63
    otrop
    -0.63
     Birthday
    -0.63
    POSITIVE LOGITS
     will
    1.08
     shall
    1.00
    shall
    0.99
     SHALL
    0.98
     would
    0.96
    will
    0.93
     should
    0.91
     may
    0.90
    OULD
    0.88
     MUST
    0.86
    Activations Density 0.082%

    No Known Activations