© 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. 8626
    Prev
    Next
    INDEX
    Explanations

    political party names

    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
    7
    +0.12
    0.6%
    503
    +0.09
    0.4%
    588
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.12
    0.02
    288
    +0.09
    0.02
    659
    +0.09
    0.02
    Negative Logits
     Lisbon
    -0.75
    iquid
    -0.72
    resses
    -0.71
     resp
    -0.71
    osure
    -0.70
    vironments
    -0.69
    selage
    -0.67
     Prairie
    -0.66
    zing
    -0.65
    lect
    -0.63
    POSITIVE LOGITS
    illion
    0.92
    ansky
    0.80
    hak
    0.79
    ataka
    0.76
     Adin
    0.75
    dra
    0.74
    lag
    0.74
    shaw
    0.73
    rative
    0.73
     challeng
    0.72
    Activations Density 0.050%

    No Known Activations