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 3072
    5. 8-RES_FS3072-JB
    6. 1477
    Prev
    Next
    INDEX
    Explanations

    information related to trade, commerce, and financial transactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    481
    +0.17
    0.8%
    84
    +0.09
    0.4%
    662
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.17
    0.04
    647
    +0.09
    0.04
    84
    +0.08
    0.03
    Negative Logits
    iste
    -0.84
    anos
    -0.79
    ager
    -0.77
    awar
    -0.75
    asley
    -0.74
    quote
    -0.74
    ANS
    -0.73
    unker
    -0.72
    oiler
    -0.71
    rone
    -0.71
    POSITIVE LOGITS
     countless
    0.90
     assorted
    0.89
     numerous
    0.85
     ensuring
    0.84
     other
    0.83
     dozens
    0.82
     innumerable
    0.82
     those
    0.81
     optionally
    0.77
     myriad
    0.77
    Activations Density 0.661%

    No Known Activations