© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5028
    Prev
    Next
    INDEX
    Explanations

    terms related to internet regulations and content filtering

    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
    480
    +0.23
    1.0%
    179
    +0.09
    0.4%
    462
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.23
    0.08
    351
    +0.09
    0.04
    70
    +0.09
    0.06
    Negative Logits
    ĸļ
    -0.73
     reminis
    -0.70
    ï¸ı
    -0.70
    nin
    -0.69
    atsuki
    -0.68
    Ùĩ
    -0.68
    _-
    -0.67
    Ô
    -0.67
    REDACTED
    -0.67
    terness
    -0.67
    POSITIVE LOGITS
     customers
    1.00
     themselves
    0.97
     their
    0.95
     subsidiaries
    0.92
     profitable
    0.91
     theirs
    0.90
     subcontract
    0.90
     certain
    0.90
     licenses
    0.88
     licences
    0.88
    Activations Density 0.541%

    No Known Activations