© 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. 8909
    Prev
    Next
    INDEX
    Explanations

    phrases related to political analysis and leadership qualities

    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
    654
    +0.11
    0.5%
    436
    +0.09
    0.4%
    679
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.11
    0.05
    654
    +0.09
    0.05
    70
    +0.09
    0.05
    Negative Logits
    phabet
    -0.89
    osures
    -0.71
    ermanent
    -0.71
    idav
    -0.70
    igham
    -0.69
    ciation
    -0.69
    epend
    -0.68
    ciating
    -0.68
    afort
    -0.65
    cellaneous
    -0.64
    POSITIVE LOGITS
    ledged
    0.73
     weakness
    0.72
     Clause
    0.71
     instinctively
    0.70
    ibly
    0.69
     weaknesses
    0.68
     danger
    0.66
    edge
    0.65
     beware
    0.64
    ingly
    0.64
    Activations Density 0.264%

    No Known Activations