© 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. 6-RES-JB
    11. 9244
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency-related terms and mentions of financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    references to cryptocurrency and related financial instruments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.89
     Scientology
    -0.69
     coli
    -0.68
    ADA
    -0.65
     Mandal
    -0.63
     Shepard
    -0.62
     Marriott
    -0.62
     Kenyan
    -0.61
     vide
    -0.61
     Scient
    -0.60
    POSITIVE LOGITS
    itiveness
    0.90
    pload
    0.86
    illin
    0.80
    ished
    0.79
    vity
    0.71
    culosis
    0.70
    icipated
    0.70
    raph
    0.69
    yip
    0.68
    elson
    0.67
    Activations Density 0.292%

    No Known Activations