© 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 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. 12604
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions and decision-making

    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
    699
    +0.10
    0.4%
    8
    +0.09
    0.4%
    367
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    8
    +0.10
    0.03
    338
    +0.09
    0.02
    485
    +0.09
    0.02
    Negative Logits
    hab
    -0.71
    sole
    -0.67
    BAT
    -0.65
    pet
    -0.62
    md
    -0.60
    eni
    -0.59
    efe
    -0.59
    tyard
    -0.59
    forts
    -0.58
    chio
    -0.58
    POSITIVE LOGITS
     surely
    1.08
     yeah
    0.99
     congratulations
    0.98
     yes
    0.86
     why
    0.83
     shouldn
    0.78
     we
    0.77
     maybe
    0.76
    ratulations
    0.76
     chances
    0.73
    Activations Density 0.035%

    No Known Activations