© 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. 10-RES-JB
    11. 5762
    Prev
    Next
    INDEX
    Explanations

    words or parts of words related to sacrifice or allegiance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sacrilege or offenses against sacred things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndra
    -0.66
    witz
    -0.63
     compr
    -0.62
     mitigation
    -0.62
     Saban
    -0.61
     Cheong
    -0.60
     elev
    -0.59
    agon
    -0.59
    WARD
    -0.57
     rarity
    -0.54
    POSITIVE LOGITS
    atible
    0.86
    etary
    0.85
    aires
    0.80
    onut
    0.77
    urate
    0.75
    CLE
    0.75
    aneous
    0.73
    irie
    0.72
    ascript
    0.69
    illi
    0.67
    Activations Density 0.120%

    No Known Activations