© 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. 2210
    Prev
    Next
    INDEX
    Explanations

    information related to security breaches and investigations

    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
    756
    +0.17
    0.8%
    87
    +0.14
    0.6%
    679
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.17
    -0.02
    679
    +0.14
    0.09
    393
    +0.09
    0.10
    Negative Logits
    ebted
    -0.77
    gae
    -0.77
     crave
    -0.74
    usterity
    -0.71
    thood
    -0.66
     utopian
    -0.66
    rene
    -0.65
     Challenges
    -0.65
     Indie
    -0.64
     Aging
    -0.64
    POSITIVE LOGITS
     contempor
    1.15
     testified
    0.97
    REDACTED
    0.96
    andestine
    0.88
    Had
    0.87
     redacted
    0.87
     presumably
    0.86
     occurred
    0.86
     briefed
    0.85
     intercepted
    0.83
    Activations Density 1.182%

    No Known Activations