© 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. 3532
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or questioning

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce questions or inquiries

    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
    upt
    -0.66
    ools
    -0.65
    kan
    -0.62
    folio
    -0.62
    roying
    -0.61
    OOL
    -0.60
    itton
    -0.58
    UP
    -0.58
    ool
    -0.57
    gdala
    -0.56
    POSITIVE LOGITS
     regards
    1.15
     to
    1.00
     well
    0.85
    well
    0.85
     far
    0.83
     follows
    0.82
    pires
    0.77
    criptions
    0.77
     evidenced
    0.77
    pects
    0.75
    Activations Density 0.103%

    No Known Activations