© 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 EvalsExportsinterp-engineNEWAPI 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. 6441
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or speculation, often involving betting or wagering

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to betting or making wagers

    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
     ACS
    -0.66
     Hyde
    -0.65
    agn
    -0.63
    ELF
    -0.62
     Occupations
    -0.62
     Administrative
    -0.61
     QC
    -0.61
     Processing
    -0.60
    levels
    -0.60
     Horror
    -0.60
    POSITIVE LOGITS
     bet
    4.05
     bets
    2.89
    bet
    2.18
    Bet
    2.16
     betting
    2.03
     Bet
    1.84
     gamble
    1.51
     BET
    1.40
     gamb
    1.35
     gam
    1.16
    Activations Density 0.014%

    No Known Activations