© 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 24576
    9. 8-RES_FS24576-JB
    11. 11049
    Prev
    Next
    INDEX
    Explanations

    technical terms and details related to product testing and evaluation

    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
    566
    +0.12
    0.6%
    326
    +0.11
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.04
    530
    +0.11
    0.05
    271
    +0.11
    0.04
    Negative Logits
    lets
    -0.72
    perties
    -0.70
    eca
    -0.69
    alk
    -0.67
    opol
    -0.65
    ae
    -0.65
    ffen
    -0.64
    uid
    -0.64
    ord
    -0.64
    ks
    -0.63
    POSITIVE LOGITS
    HEAD
    1.48
     FANTASY
    1.44
    BOOK
    1.41
    WORK
    1.41
     REPORT
    1.41
     WEEK
    1.41
    FORM
    1.41
    MAN
    1.40
     STORY
    1.39
    WOR
    1.39
    Activations Density 0.166%

    No Known Activations