© 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 49152
    9. 8-RES_FS49152-JB
    11. 41638
    Prev
    Next
    INDEX
    Explanations

    mentions of legislation and political actions

    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
    547
    +0.09
    0.5%
    117
    +0.09
    0.5%
    333
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    117
    +0.09
    0.03
    547
    +0.09
    0.02
    470
    +0.09
    0.02
    Negative Logits
    ruary
    -0.71
    theless
    -0.70
    bara
    -0.69
    mberg
    -0.63
     psychiat
    -0.62
    vertisements
    -0.62
    ptin
    -0.60
    prisingly
    -0.59
    amorph
    -0.58
    owship
    -0.57
    POSITIVE LOGITS
     Kavanaugh
    0.80
     accuser
    0.72
     Dems
    0.70
    ']
    0.68
    ]}
    0.65
     intel
    0.64
     probe
    0.64
    ').
    0.64
    %]
    0.62
    «ĺ
    0.61
    Activations Density 0.041%

    No Known Activations