© 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 12288
    9. 8-RES_FS12288-JB
    11. 10497
    Prev
    Next
    INDEX
    Explanations

    references to capturing or protecting animals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    +0.23
    1.1%
    72
    +0.10
    0.5%
    620
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.23
    0.08
    529
    +0.10
    0.06
    408
    +0.09
    0.10
    Negative Logits
    Marx
    -0.72
    Plot
    -0.71
     Comedy
    -0.64
    issors
    -0.64
    Lenin
    -0.64
    atsuki
    -0.63
    BBC
    -0.62
    verb
    -0.62
    Mom
    -0.62
    inho
    -0.61
    POSITIVE LOGITS
     compliance
    0.77
     compliant
    0.77
     affected
    0.74
     discriminatory
    0.71
     practices
    0.71
     similar
    0.71
     impacted
    0.71
     federally
    0.69
     nationwide
    0.69
     pending
    0.68
    Activations Density 1.656%

    No Known Activations