© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 20801
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to sports events, locations, and personalities

    oai_token-act-pair · gpt-3.5-turbo

    references to sporting events and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ibid
    -0.74
     ®
    -0.68
    )",
    -0.68
     constitu
    -0.66
    SOURCE
    -0.65
     Citiz
    -0.64
     Somalia
    -0.62
     UNCLASSIFIED
    -0.61
     secrecy
    -0.60
    ossier
    -0.60
    POSITIVE LOGITS
     Stadium
    1.10
    ESPN
    1.00
    sports
    0.97
     Trophy
    0.94
    Sports
    0.93
     jerseys
    0.93
     Sports
    0.93
     Coliseum
    0.92
     matchup
    0.90
    juries
    0.90
    Activations Density 0.860%

    No Known Activations