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. 23089
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "salami" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered 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
    564
    +0.15
    0.7%
    490
    +0.10
    0.5%
    275
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    564
    +0.15
    0.05
    698
    +0.10
    0.04
    691
    +0.10
    0.03
    Negative Logits
     Polk
    -0.73
     Nev
    -0.68
    IRD
    -0.67
    fair
    -0.64
     Cow
    -0.64
     Jem
    -0.63
    ãĤ±
    -0.63
    Nev
    -0.61
     Kim
    -0.59
    OSP
    -0.59
    POSITIVE LOGITS
    ragon
    0.78
    acular
    0.76
    ttes
    0.74
    geries
    0.70
    urations
    0.70
    ectomy
    0.68
    aneously
    0.68
    osite
    0.68
    ield
    0.65
    rect
    0.65
    Activations Density 0.237%

    No Known Activations