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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1639
    Prev
    Next
    INDEX
    Explanations

    information related to legal cases involving sexual misconduct with minors

    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
    121
    +0.10
    0.5%
    545
    +0.10
    0.5%
    47
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.10
    0.05
    694
    +0.10
    0.03
    235
    +0.10
    0.04
    Negative Logits
    pmwiki
    -1.01
    NetMessage
    -0.83
    inventoryQuantity
    -0.78
     certs
    -0.77
    xit
    -0.74
    ãĥķãĤ©
    -0.71
    OTAL
    -0.69
     Repair
    -0.68
    govtrack
    -0.68
     landfall
    -0.68
    POSITIVE LOGITS
     underage
    1.37
     sexually
    1.16
     inappropriately
    1.16
     genitals
    1.16
     prostitutes
    1.08
     sexual
    1.08
     breasts
    1.06
    girlfriend
    1.05
     prostitute
    1.04
     genital
    1.03
    Activations Density 0.306%

    No Known Activations