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. 0-RES-JB
    6. 8894
    Prev
    Next
    INDEX
    Explanations

    mentions of a sports team named "Hawks" and associated activities such as games, players, and bids

    oai_token-act-pair · gpt-3.5-turbo

    references to the Hawks, likely a sports team

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ork
    -0.73
    Gi
    -0.69
    rect
    -0.68
    ér
    -0.68
    ummy
    -0.67
    prim
    -0.65
     chronological
    -0.64
    :/
    -0.64
     mirror
    -0.63
     vir
    -0.62
    POSITIVE LOGITS
     Hawks
    4.12
     Hawk
    2.22
     Falcons
    2.03
     Blackhawks
    2.01
    hawks
    1.95
     hawk
    1.52
    awks
    1.49
     Braves
    1.47
    hawk
    1.44
     Seahawks
    1.39
    Activations Density 0.015%

    No Known Activations