Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 449
    Prev
    Next
    INDEX
    Explanations

    geographical locations and related events

    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
    +0.12
    0.5%
    447
    +0.11
    0.5%
    324
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.17
    547
    +0.11
    0.08
    391
    +0.10
    0.06
    Negative Logits
    athi
    -0.67
    %%%%
    -0.57
     collaboration
    -0.56
    %"
    -0.55
     prev
    -0.55
    Trend
    -0.54
     resemblance
    -0.53
    %%
    -0.53
    \":
    -0.53
    )}
    -0.51
    POSITIVE LOGITS
     ASAP
    1.00
     undet
    1.00
     via
    0.95
     fray
    0.94
     whence
    0.93
    livion
    0.91
     unnoticed
    0.89
     coffers
    0.85
     quicker
    0.79
     sooner
    0.77
    Activations Density 2.740%

    No Known Activations