© 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 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. 9103
    Prev
    Next
    INDEX
    Explanations

    keywords related to software vulnerabilities and security issues

    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
    481
    +0.12
    0.6%
    739
    +0.11
    0.5%
    211
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.12
    0.02
    288
    +0.11
    0.02
    651
    +0.10
    0.02
    Negative Logits
    essional
    -0.76
    thumbnails
    -0.74
    ikk
    -0.72
     Colon
    -0.72
    axis
    -0.70
    ihu
    -0.69
    ohydrate
    -0.68
    ndum
    -0.67
    eree
    -0.66
     adject
    -0.65
    POSITIVE LOGITS
    CVE
    1.32
     CVE
    1.27
     vulnerabilities
    1.11
    ulnerability
    1.04
     patched
    1.00
     vulnerability
    1.00
     exploit
    0.97
    ulner
    0.96
     exploited
    0.89
     plag
    0.87
    Activations Density 0.057%

    No Known Activations