© 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 49152
    9. 8-RES_FS49152-JB
    11. 45843
    Prev
    Next
    INDEX
    Explanations

    words associated with governmental or political dissent

    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
    587
    +0.11
    0.5%
    463
    +0.11
    0.5%
    4
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    4
    +0.11
    0.01
    63
    +0.11
    0.01
    463
    +0.11
    0.01
    Negative Logits
    HAHAHAHA
    -0.74
    bian
    -0.68
     bund
    -0.67
    cham
    -0.63
     Gingrich
    -0.63
    RC
    -0.63
    inventoryQuantity
    -0.62
    HAHA
    -0.61
     Wem
    -0.60
     Springfield
    -0.60
    POSITIVE LOGITS
    ments
    1.44
    ificant
    1.24
    eous
    1.00
    mentation
    0.96
    antly
    0.94
    s
    0.94
    atures
    0.94
    ancy
    0.92
    ity
    0.90
    ific
    0.89
    Activations Density 0.008%

    No Known Activations