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 49152
    5. 8-RES_FS49152-JB
    6. 26114
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses

    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
    311
    +0.12
    0.6%
    57
    +0.11
    0.5%
    372
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.12
    0.01
    609
    +0.11
    0.01
    311
    +0.10
    0.01
    Negative Logits
     expulsion
    -0.71
     surn
    -0.65
     recess
    -0.65
     handling
    -0.64
     conformity
    -0.62
     sway
    -0.62
     saline
    -0.61
     succeeding
    -0.61
     quart
    -0.60
     inadequ
    -0.60
    POSITIVE LOGITS
    www
    1.16
    ://
    0.99
    natureconservancy
    0.99
    forum
    0.97
     www
    0.93
    ww
    0.89
    forums
    0.84
    ctl
    0.84
    hr
    0.81
    youtu
    0.81
    Activations Density 0.006%

    No Known Activations