© 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 EvalsExportsAPI 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. 1906
    Prev
    Next
    INDEX
    Explanations

    references to punitive measures related to law enforcement, particularly jail time

    oai_token-act-pair · gpt-3.5-turbo

    mentions of jail or imprisonment

    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
     Investors
    -0.73
    yip
    -0.72
     Illum
    -0.71
     Scotia
    -0.71
    Downloadha
    -0.70
     Nare
    -0.70
     ATK
    -0.68
     Rossi
    -0.65
    uyomi
    -0.65
     magnification
    -0.63
    POSITIVE LOGITS
    break
    1.18
    broken
    1.14
    breaks
    1.09
    house
    1.02
    rooms
    0.96
    breaking
    0.94
    breakers
    0.94
    alde
    0.92
    itory
    0.84
     jails
    0.84
    Activations Density 0.031%

    No Known Activations