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. 43360
    Prev
    Next
    INDEX
    Explanations

    instances of the word "race" and its variations

    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
    447
    +0.11
    0.5%
    620
    +0.11
    0.5%
    647
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.11
    0.02
    24
    +0.11
    0.02
    620
    +0.10
    0.01
    Negative Logits
    olia
    -0.76
    iar
    -0.76
    oca
    -0.75
    arial
    -0.73
    tymology
    -0.72
    lishes
    -0.71
    berra
    -0.71
    vironment
    -0.67
    osis
    -0.66
    iated
    -0.65
    POSITIVE LOGITS
    horse
    1.31
    course
    1.29
    cars
    1.05
    bike
    1.04
    car
    0.98
    nell
    0.84
    runners
    0.83
    runner
    0.83
     bikes
    0.82
    goers
    0.79
    Activations Density 0.018%

    No Known Activations