© 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. 9561
    Prev
    Next
    INDEX
    Explanations

    mentions of the politician named McGuinness

    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
    476
    +0.10
    0.5%
    420
    +0.10
    0.5%
    120
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.02
    659
    +0.10
    0.02
    232
    +0.10
    0.02
    Negative Logits
    ãĥ³ãĤ¸
    -0.85
    ãĥ¼ãĥĨãĤ£
    -0.85
    itarian
    -0.84
    ication
    -0.80
    ãĤ¼
    -0.77
    ãĤ¤ãĥĪ
    -0.75
    ation
    -0.74
    ãĥ¼ãĥ
    -0.74
    tics
    -0.73
    oglu
    -0.73
    POSITIVE LOGITS
    inness
    0.85
    ionage
    0.82
    idge
    0.82
    ORTS
    0.78
    resso
    0.76
    lette
    0.74
    pring
    0.71
    olicy
    0.71
    redo
    0.69
    isters
    0.69
    Activations Density 0.044%

    No Known Activations