© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 4360
    Prev
    Next
    INDEX
    Explanations

    verbs related to political actions and discussions

    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
    13
    +0.11
    0.5%
    184
    +0.11
    0.5%
    567
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.11
    0.07
    184
    +0.11
    0.04
    641
    +0.11
    0.05
    Negative Logits
     supposedly
    -0.65
     entit
    -0.62
     viz
    -0.57
     wander
    -0.57
     typing
    -0.57
     piled
    -0.56
    Downloadha
    -0.56
    agues
    -0.56
     cla
    -0.54
     passers
    -0.54
    POSITIVE LOGITS
    cipled
    0.99
     ASAP
    0.96
     urgently
    0.93
    cknow
    0.87
     rethink
    0.85
     heed
    0.81
     reconsider
    0.79
     humility
    0.77
     wisely
    0.76
    fitting
    0.76
    Activations Density 0.321%

    No Known Activations