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. 1092
    Prev
    Next
    INDEX
    Explanations

    names of authors and titles of academic papers

    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
    612
    +0.11
    0.5%
    456
    +0.09
    0.4%
    393
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.11
    0.02
    673
    +0.09
    0.02
    284
    +0.09
    0.02
    Negative Logits
    interstitial
    -0.86
     applicable
    -0.72
    olves
    -0.68
    pread
    -0.68
     upside
    -0.68
     fused
    -0.65
    itol
    -0.65
    Bound
    -0.64
    Applications
    -0.63
    overs
    -0.63
    POSITIVE LOGITS
     supra
    1.20
     et
    1.10
     Jr
    0.86
     Associates
    0.85
     JA
    0.84
     JJ
    0.83
     LLP
    0.83
     JM
    0.79
     RJ
    0.78
     Constantin
    0.78
    Activations Density 0.058%

    No Known Activations