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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15350
    Prev
    Next
    INDEX
    Explanations

    sports scores in the format of "team A X - Y team B"

    oai_token-act-pair · gpt-3.5-turbo

    scorelines and statistics from sports events

    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
     SX
    -0.68
     Loll
    -0.64
     Peck
    -0.63
     Aval
    -0.62
     Mara
    -0.61
     CES
    -0.60
     Bei
    -0.60
     Chop
    -0.59
     Hoo
    -0.59
     RTX
    -0.59
    POSITIVE LOGITS
    point
    1.11
    straight
    1.07
    gage
    0.97
    win
    0.97
    iron
    0.96
    pointer
    0.96
    game
    0.95
    year
    0.94
    seed
    0.93
    minute
    0.92
    Activations Density 0.057%

    No Known Activations