© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7317
    Prev
    Next
    INDEX
    Explanations

    instructions and technical terms in a foreign language

    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
    237
    +0.12
    0.6%
    230
    +0.11
    0.5%
    474
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.03
    227
    +0.11
    0.02
    81
    +0.11
    0.03
    Negative Logits
    imen
    -0.69
     undert
    -0.69
     Nightmare
    -0.69
     upt
    -0.68
    883
    -0.67
    owski
    -0.66
    023
    -0.66
    eki
    -0.65
     Tsu
    -0.65
     Resp
    -0.64
    POSITIVE LOGITS
    g
    1.27
    Gs
    1.26
    G
    1.20
    GY
    1.19
    gian
    1.14
    gs
    1.09
    gm
    1.08
    gel
    1.08
    gil
    1.07
    gi
    1.07
    Activations Density 0.141%

    No Known Activations