© 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. 0-RES-JB
    11. 16366
    Prev
    Next
    INDEX
    Explanations

    words related to stakes and high-risk situations

    oai_token-act-pair · gpt-3.5-turbo

    references to high-risk or high-reward situations

    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
    iform
    -0.78
    olor
    -0.73
    UI
    -0.69
     Library
    -0.64
     Disorder
    -0.63
    Function
    -0.62
    lement
    -0.61
    apan
    -0.61
    uish
    -0.61
    orter
    -0.59
    POSITIVE LOGITS
     stakes
    4.49
     stake
    2.11
    stakes
    2.05
     bets
    1.16
     prizes
    1.10
     payoff
    1.10
     ropes
    1.05
     odds
    1.04
     ante
    1.03
     trenches
    1.00
    Activations Density 0.014%

    No Known Activations