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 24576
    5. 8-RES_FS24576-JB
    6. 21741
    Prev
    Next
    INDEX
    Explanations

    direct quotes emphasizing a particular point or opinion

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    +0.16
    0.7%
    717
    +0.10
    0.5%
    458
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.16
    0.02
    498
    +0.10
    0.02
    184
    +0.10
    0.02
    Negative Logits
     largeDownload
    -0.83
    acker
    -0.70
    »Ĵ
    -0.64
    Ͻ
    -0.64
    ĺħ
    -0.63
    ccording
    -0.61
    ?????-
    -0.61
    ixel
    -0.60
    ibal
    -0.60
    pora
    -0.60
    POSITIVE LOGITS
    ifiable
    1.12
     ones
    0.82
     ours
    0.75
    ones
    0.74
     anymore
    0.73
     yours
    0.73
    ifications
    0.73
    here
    0.70
    onto
    0.70
    ional
    0.67
    Activations Density 0.031%

    No Known Activations