© 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 EvalsExportsinterp-engineNEWAPI 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. 16161
    Prev
    Next
    INDEX
    Explanations

    political or social justice-related discussions and statements

    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
    +0.16
    0.8%
    373
    +0.16
    0.8%
    139
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.16
    0.05
    425
    +0.16
    0.04
    368
    +0.13
    0.04
    Negative Logits
    gress
    -0.66
    ize
    -0.64
    ":"/
    -0.64
    itized
    -0.64
     (>
    -0.63
    OTUS
    -0.62
    DON
    -0.61
    ente
    -0.60
    isSpecialOrderable
    -0.60
    Switch
    -0.60
    POSITIVE LOGITS
     wrote
    0.80
     founded
    0.77
     joined
    0.74
     congratulated
    0.71
     welcomed
    0.70
     penned
    0.69
     persuaded
    0.69
     intervened
    0.68
     testified
    0.68
     hired
    0.68
    Activations Density 0.120%

    No Known Activations