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. 46155
    Prev
    Next
    INDEX
    Explanations

    references to individuals named Tracy or related names

    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
    0
    +0.13
    0.6%
    737
    +0.10
    0.5%
    346
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.01
    0
    +0.10
    0.01
    346
    +0.10
    0.01
    Negative Logits
    rated
    -1.05
    ration
    -0.94
    ername
    -0.84
    growth
    -0.83
    rate
    -0.81
    rates
    -0.79
    rator
    -0.79
     indo
    -0.76
    ktop
    -0.75
    nown
    -0.74
    POSITIVE LOGITS
     Hick
    1.08
     McGr
    1.04
     Olson
    1.02
     Chapman
    0.97
     Morgan
    0.94
     Kelley
    0.87
     Adams
    0.84
     MacDonald
    0.83
     Tracy
    0.82
     Keller
    0.82
    Activations Density 0.008%

    No Known Activations