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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 562
    Prev
    Next
    INDEX
    Explanations

    references to legal and governmental topics and statistics

    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
    87
    +0.24
    1.3%
    756
    +0.16
    0.9%
    459
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.24
    -0.04
    87
    +0.16
    -0.09
    459
    +0.16
    0.14
    Negative Logits
    ileaks
    -0.62
     (@
    -0.60
     Collider
    -0.59
     tonight
    -0.59
     Osw
    -0.58
     Ultron
    -0.58
     yesterday
    -0.57
     Cancel
    -0.56
     Verse
    -0.55
     Tomorrow
    -0.54
    POSITIVE LOGITS
    often
    1.01
     often
    0.92
     routinely
    0.92
    entimes
    0.91
     rarely
    0.83
     specialize
    0.82
     typically
    0.82
     themselves
    0.81
     invariably
    0.81
     frequently
    0.80
    Activations Density 6.454%

    No Known Activations