© 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. 11-RES-JB
    11. 21104
    Prev
    Next
    INDEX
    Explanations

    apologies or statements of regret

    oai_token-act-pair · gpt-3.5-turbo

    expressions of apology and regret

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FTWARE
    -0.79
    DragonMagazine
    -0.78
    bard
    -0.75
    kefeller
    -0.73
    fman
    -0.69
    atown
    -0.67
    vantage
    -0.67
    otic
    -0.66
    Ready
    -0.64
     Mehran
    -0.64
    POSITIVE LOGITS
     mistakes
    1.25
     inconvenience
    1.16
     inconven
    1.14
    mist
    1.05
     hurting
    1.03
     unintentional
    1.02
     unintentionally
    1.01
     offended
    1.00
     ruining
    1.00
     sins
    1.00
    Activations Density 0.145%

    No Known Activations