Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 43418
    Prev
    Next
    INDEX
    Explanations

    instances of the word "right"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    50
    +0.11
    0.5%
    594
    +0.09
    0.4%
    289
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.11
    0.04
    594
    +0.09
    0.03
    70
    +0.09
    0.03
    Negative Logits
    aples
    -0.70
    igmat
    -0.64
    arette
    -0.64
     cellul
    -0.60
    idated
    -0.60
    âĢ¢
    -0.59
    ulative
    -0.59
    ĸļ
    -0.58
    raved
    -0.58
    advert
    -0.58
    POSITIVE LOGITS
    eous
    1.09
     smack
    0.91
     fielder
    0.84
     wing
    0.75
    move
    0.71
     winger
    0.69
    ward
    0.68
    ocrin
    0.67
    Ĥİ
    0.66
    behind
    0.66
    Activations Density 0.025%

    No Known Activations