© 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. 8586
    Prev
    Next
    INDEX
    Explanations

    statements made in formal settings, specifically within legal and governmental contexts

    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
    467
    +0.11
    0.5%
    640
    +0.10
    0.5%
    120
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.11
    0.09
    618
    +0.10
    0.07
    430
    +0.10
    0.08
    Negative Logits
     underestimate
    -0.85
     lately
    -0.82
     underestimated
    -0.79
     mismatch
    -0.77
     setups
    -0.77
     monop
    -0.76
     landscape
    -0.76
     unpredict
    -0.75
     sideways
    -0.75
     sometimes
    -0.74
    POSITIVE LOGITS
    Statement
    0.96
    Refer
    0.92
    <|endoftext|>
    0.90
     Refer
    0.89
    Shares
    0.88
    Comment
    0.84
    Additional
    0.83
     "...
    0.83
     Additionally
    0.82
     Accessed
    0.82
    Activations Density 0.361%

    No Known Activations