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. 43434
    Prev
    Next
    INDEX
    Explanations

    instances of the word "more" in various 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
    726
    +0.14
    0.6%
    402
    +0.11
    0.5%
    460
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    726
    +0.14
    0.02
    402
    +0.11
    0.02
    585
    +0.10
    0.02
    Negative Logits
    ORS
    -0.73
    gee
    -0.72
    pper
    -0.70
    minus
    -0.70
    assis
    -0.70
    ogens
    -0.70
    poke
    -0.69
    maid
    -0.68
    eson
    -0.68
    master
    -0.66
    POSITIVE LOGITS
     importantly
    0.76
     sophisticated
    0.75
     occurrences
    0.75
     frustrated
    0.73
     invitations
    0.73
     intrusive
    0.71
     refined
    0.71
     noticeable
    0.71
     worrisome
    0.70
     exciting
    0.70
    Activations Density 0.023%

    No Known Activations