© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 13450
    Prev
    Next
    INDEX
    Explanations

    political and news-related terms or phrases

    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
    87
    +0.11
    0.6%
    64
    +0.09
    0.5%
    141
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.11
    -0.02
    620
    +0.09
    0.02
    575
    +0.09
    0.07
    Negative Logits
    )--
    -0.53
     Anon
    -0.53
    estern
    -0.50
     Ort
    -0.49
     Canaver
    -0.47
     Myst
    -0.47
     Maurit
    -0.45
     gathers
    -0.44
     pictured
    -0.44
     Hin
    -0.44
    POSITIVE LOGITS
    $.
    0.84
    *.
    0.82
    .?
    0.80
    _.
    0.79
    '.
    0.75
    %.
    0.74
    >.
    0.72
    ãĢĤ
    0.72
     guiName
    0.68
    +.
    0.68
    Activations Density 1.784%

    No Known Activations