© 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. 8-RES-JB
    11. 16724
    Prev
    Next
    INDEX
    Explanations

    mentions of the game show "Jeopardy"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Jeopardy" and its variants

    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
    ancial
    -0.70
     scen
    -0.66
    ificantly
    -0.66
    heartedly
    -0.65
    ãĥĥãĤ¯
    -0.65
    ãĥ´ãĤ¡
    -0.65
    istics
    -0.64
    iosity
    -0.64
    IFIED
    -0.63
    raviolet
    -0.63
    POSITIVE LOGITS
    opard
    1.29
    hovah
    1.14
    pee
    1.00
    zeb
    0.97
    apons
    0.94
    annie
    0.93
    eps
    0.92
    ansen
    0.91
    ans
    0.90
    lde
    0.88
    Activations Density 0.022%

    No Known Activations