© 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. 23928
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistics related to contributions and events

    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
    8
    +0.10
    0.5%
    398
    +0.10
    0.5%
    226
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.10
    0.01
    362
    +0.10
    0.04
    609
    +0.10
    0.03
    Negative Logits
    instead
    -0.68
     compared
    -0.61
    AME
    -0.61
     resembled
    -0.59
    Registered
    -0.59
    adh
    -0.57
    artz
    -0.57
     compares
    -0.56
    ixties
    -0.56
     Peck
    -0.56
    POSITIVE LOGITS
     accompanying
    0.80
    cellaneous
    0.76
     thereto
    0.76
     obligatory
    0.74
     others
    0.71
     counterparts
    0.71
     caveats
    0.70
    catentry
    0.70
     ones
    0.69
     commentary
    0.69
    Activations Density 0.395%

    No Known Activations