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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15463
    Prev
    Next
    INDEX
    Explanations

    sports match-ups or competitions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "vs" indicating matchups or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.75
     ancest
    -0.66
    ospons
    -0.62
     appre
    -0.62
     crossings
    -0.61
    estern
    -0.60
     liberties
    -0.59
    wcs
    -0.59
     evenings
    -0.59
    cffffcc
    -0.59
    POSITIVE LOGITS
    .,
    1.09
    .-
    1.02
    .:
    1.00
    .
    0.99
    .;
    0.91
    .?
    0.88
    ._
    0.87
    ./
    0.79
     RHP
    0.78
    .–
    0.77
    Activations Density 0.025%

    No Known Activations