Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 37138
    Prev
    Next
    INDEX
    Explanations

    references to domestic violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    288
    +0.15
    0.7%
    152
    +0.14
    0.6%
    146
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.15
    0.02
    146
    +0.14
    0.01
    616
    +0.10
    0.01
    Negative Logits
    */(
    -0.95
    uyomi
    -0.94
     GOODMAN
    -0.91
    umper
    -0.81
    UMP
    -0.80
    SOURCE
    -0.78
    uden
    -0.78
    Reviewer
    -0.75
    DragonMagazine
    -0.74
    akeru
    -0.72
    POSITIVE LOGITS
     Violence
    1.03
     violence
    1.01
     affairs
    0.97
     tranqu
    0.90
     abusers
    0.87
     abuser
    0.82
     abuse
    0.82
    estic
    0.82
    violence
    0.81
     appliances
    0.81
    Activations Density 0.008%

    No Known Activations