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. 8-RES-JB
    6. 15901
    Prev
    Next
    INDEX
    Explanations

    mentions of American football teams and related events

    oai_token-act-pair · gpt-3.5-turbo

    references to American football games and related teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.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

    Negative Logits
    é¾įåĸļ士
    -0.59
    onyms
    -0.57
    ":[{"
    -0.56
     horizont
    -0.53
     Kaf
    -0.51
    SourceFile
    -0.49
    etically
    -0.49
     nonetheless
    -0.49
    ividually
    -0.49
    oyal
    -0.49
    POSITIVE LOGITS
     sponsoring
    0.62
    runs
    0.49
     legalized
    0.48
     holiday
    0.48
     subsidized
    0.48
     WW
    0.48
    iversary
    0.48
     Halloween
    0.47
    cember
    0.47
     sponsors
    0.46
    Activations Density 1.990%

    No Known Activations