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. 43372
    Prev
    Next
    INDEX
    Explanations

    references to file paths and directory structures

    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
    642
    +0.10
    0.5%
    622
    +0.10
    0.4%
    457
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    627
    +0.10
    0.01
    530
    +0.10
    0.02
    412
    +0.09
    0.02
    Negative Logits
    tein
    -0.66
     rake
    -0.66
    milo
    -0.61
    itiveness
    -0.60
    reads
    -0.60
    illet
    -0.59
    antz
    -0.58
    ruff
    -0.58
     Deadly
    -0.58
     exec
    -0.57
    POSITIVE LOGITS
    ãĥĺãĥ©
    0.79
    ãĤ¼ãĤ¦ãĤ¹
    0.78
    achu
    0.76
     Territories
    0.76
     kindred
    0.69
     Territory
    0.68
    arta
    0.68
    ãĥIJ
    0.66
    itol
    0.66
    thia
    0.65
    Activations Density 0.079%

    No Known Activations