Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 2-RES-JB
    6. 16208
    Prev
    Next
    INDEX
    Explanations

    instances of the word "match."

    oai_token-act-pair · gpt-3.5-turbo

    references to various sports matches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.82
    irtual
    -0.73
    gone
    -0.66
    umn
    -0.65
    ä¼
    -0.64
    otom
    -0.63
    sie
    -0.62
    Vert
    -0.61
    FORMATION
    -0.61
    shown
    -0.61
    POSITIVE LOGITS
     matches
    0.99
     match
    0.97
    match
    0.86
    maker
    0.85
    making
    0.84
    makers
    0.83
     Match
    0.82
    ees
    0.72
    eers
    0.72
    fit
    0.69
    Activations Density 0.013%

    No Known Activations