© 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. 12087
    Prev
    Next
    INDEX
    Explanations

    names of educational institutions, job titles, and financial terms

    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
    314
    +0.20
    0.9%
    727
    +0.11
    0.5%
    184
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.20
    0.04
    314
    +0.11
    0.00
    727
    +0.10
    0.04
    Negative Logits
     ..."
    -0.71
     âĢ¦"
    -0.67
    .","
    -0.66
    ?ãĢį
    -0.66
     Frie
    -0.62
    ?".
    -0.61
    .''
    -0.60
     fert
    -0.60
     grain
    -0.59
    .�
    -0.59
    POSITIVE LOGITS
    jamin
    1.11
    odore
    1.05
    resa
    1.03
    etheless
    1.02
    dinand
    0.98
    ropolitan
    0.92
    foundland
    0.92
    intosh
    0.86
    bidden
    0.86
    negie
    0.85
    Activations Density 0.360%

    No Known Activations