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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11250
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, specifically related to the city of Indianapolis

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of Indianapolis and its associated sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vana
    -0.88
    uchin
    -0.87
    ramid
    -0.80
    ition
    -0.77
    ascript
    -0.77
    eor
    -0.75
    istics
    -0.73
    geoning
    -0.72
    ebook
    -0.72
    bley
    -0.70
    POSITIVE LOGITS
     Colts
    1.14
    apolis
    1.02
     Indy
    0.88
     Pacers
    0.86
     Indianapolis
    0.82
     Speedway
    0.80
     Motor
    0.74
     Eleven
    0.73
     Kear
    0.70
     Colt
    0.70
    Activations Density 0.015%

    No Known Activations