© 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. 1891
    Prev
    Next
    INDEX
    Explanations

    questions or statements expressing confusion or curiosity

    oai_token-act-pair · gpt-3.5-turbo

    negative contractions and questioning phrases

    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
    urst
    -0.80
    Fra
    -0.71
    nants
    -0.67
     Fant
    -0.63
    furt
    -0.63
    à¼
    -0.62
     Frag
    -0.62
     Puzzles
    -0.61
     Flav
    -0.61
     Vand
    -0.60
    POSITIVE LOGITS
     sooner
    1.01
    itia
    0.83
     reinvest
    0.81
     adequately
    0.76
     properly
    0.72
     prosecute
    0.70
     prosec
    0.70
     reciproc
    0.68
    ounty
    0.68
     vacc
    0.67
    Activations Density 0.145%

    No Known Activations