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. 43339
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "tick" in various forms or contexts

    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
    649
    +0.12
    0.5%
    285
    +0.11
    0.5%
    121
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.01
    121
    +0.11
    0.01
    603
    +0.10
    0.01
    Negative Logits
    ocal
    -0.69
    IZE
    -0.65
     Dakota
    -0.63
    ocally
    -0.63
    ¬¼
    -0.61
    ruciating
    -0.61
    ONT
    -0.60
    isSpecialOrderable
    -0.60
    icably
    -0.58
     Columb
    -0.58
    POSITIVE LOGITS
    lers
    1.13
    lish
    1.12
    ety
    1.10
    ling
    1.05
    les
    1.02
    boxes
    0.95
    led
    0.95
    eting
    0.93
    box
    0.92
    buck
    0.90
    Activations Density 0.008%

    No Known Activations