© 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 24576
    9. 8-RES_FS24576-JB
    11. 22064
    Prev
    Next
    INDEX
    Explanations

    phrases that convey messages or signals related to democracy and civic participation

    oai_token-act-pair · gpt-4o-miniTriggered 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
    690
    +0.10
    0.5%
    252
    +0.10
    0.5%
    633
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    252
    +0.10
    0.04
    13
    +0.10
    0.04
    172
    +0.10
    0.04
    Negative Logits
     submitting
    -0.72
     Conquer
    -0.63
     submit
    -0.59
     Kare
    -0.59
     thrive
    -0.58
     sacrificed
    -0.58
     conquered
    -0.58
    anian
    -0.57
     Submission
    -0.57
     succeeds
    -0.56
    POSITIVE LOGITS
     morale
    0.88
     impression
    0.85
     credibility
    0.79
     suspicions
    0.78
    emi
    0.78
     surpr
    0.76
     impetus
    0.75
     une
    0.74
     tension
    0.73
     confidence
    0.73
    Activations Density 0.280%

    No Known Activations