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. 1-RES-JB
    6. 24361
    Prev
    Next
    INDEX
    Explanations

    specific references or mentions of the term "Match"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Match" or related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umn
    -0.73
    JC
    -0.71
    pez
    -0.71
    KN
    -0.70
    jc
    -0.69
    raft
    -0.67
    irtual
    -0.66
     orally
    -0.66
    cember
    -0.64
    issan
    -0.63
    POSITIVE LOGITS
     Match
    1.41
    match
    1.05
    Match
    1.04
     matches
    0.94
     match
    0.87
     Bots
    0.86
    ing
    0.84
     Ratings
    0.81
     Finder
    0.79
    makers
    0.76
    Activations Density 0.007%

    No Known Activations