© 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. 8895
    Prev
    Next
    INDEX
    Explanations

    keywords related to school safety concerns, threats, and incidents

    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
    519
    +0.11
    0.5%
    113
    +0.10
    0.4%
    215
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.11
    0.03
    485
    +0.10
    0.02
    519
    +0.09
    0.02
    Negative Logits
     Chains
    -0.70
     Cors
    -0.64
     Shipping
    -0.59
    obar
    -0.57
    assis
    -0.56
    tera
    -0.55
     Centauri
    -0.54
     triumphant
    -0.54
    agate
    -0.54
     mutated
    -0.54
    POSITIVE LOGITS
     taught
    1.14
     curriculum
    1.06
    girls
    1.05
     syll
    1.02
     instructors
    1.01
     curric
    0.96
     instructor
    0.95
     teachers
    0.95
     Teachers
    0.94
     teaches
    0.94
    Activations Density 0.050%

    No Known Activations