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. 46154
    Prev
    Next
    INDEX
    Explanations

    instances of agreement or consent

    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
    373
    +0.13
    0.6%
    247
    +0.12
    0.5%
    7
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.13
    0.01
    7
    +0.12
    0.01
    208
    +0.11
    0.01
    Negative Logits
     Roads
    -0.69
     Sparrow
    -0.64
     Tycoon
    -0.61
    aval
    -0.61
    pex
    -0.59
    minecraft
    -0.59
    anus
    -0.59
    esan
    -0.58
     Moroc
    -0.58
    Luck
    -0.58
    POSITIVE LOGITS
     indemn
    0.75
    reements
    0.73
     subscrib
    0.72
    emn
    0.72
    ably
    0.71
    SOURCE
    0.71
    reement
    0.71
    claimer
    0.70
    awaru
    0.68
     agreement
    0.67
    Activations Density 0.007%

    No Known Activations