© 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. 17455
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and their actions or characteristics

    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
    599
    +0.12
    0.6%
    100
    +0.11
    0.5%
    185
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.12
    0.06
    482
    +0.11
    0.05
    373
    +0.11
    -0.03
    Negative Logits
     EDITION
    -0.69
     mine
    -0.67
     mould
    -0.62
     sim
    -0.62
     seam
    -0.61
     Fortune
    -0.60
     brill
    -0.59
     MU
    -0.58
     rall
    -0.57
    ionage
    -0.56
    POSITIVE LOGITS
    Population
    0.76
    rawdownloadcloneembedreportprint
    0.75
    ļéĨĴ
    0.73
    lehem
    0.72
    erion
    0.71
    âĶĢâĶĢâĶĢâĶĢ
    0.70
    skirts
    0.67
    Reviewer
    0.65
    ajor
    0.64
    Synopsis
    0.63
    Activations Density 0.346%

    No Known Activations