© 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. 1253
    Prev
    Next
    INDEX
    Explanations

    proper nouns and 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
    267
    +0.14
    0.6%
    618
    +0.11
    0.5%
    22
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.02
    232
    +0.11
    0.02
    326
    +0.11
    0.02
    Negative Logits
     Springs
    -0.82
    ĺħ
    -0.81
    ħĭ
    -0.73
    aptic
    -0.73
    enture
    -0.69
    nesota
    -0.66
     Spaces
    -0.66
    2020
    -0.66
     airborne
    -0.64
    vious
    -0.64
    POSITIVE LOGITS
    ijn
    1.05
    raine
    0.94
    nuts
    0.85
    nut
    0.85
    ca
    0.77
    bie
    0.75
    rael
    0.75
    IENT
    0.74
    heet
    0.74
    wyn
    0.73
    Activations Density 0.037%

    No Known Activations