© 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. 2792
    Prev
    Next
    INDEX
    Explanations

    questions starting with "how" or "what" such as "howling" or "what if"

    oai_token-act-pair · gpt-3.5-turbo

    questions and inquiries related to actions and methods

    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
     Mechdragon
    -0.66
     autonomous
    -0.61
     refining
    -0.60
     infiltr
    -0.59
     silenced
    -0.59
     qualified
    -0.58
     compens
    -0.58
     shedding
    -0.58
     wise
    -0.57
     compensated
    -0.57
    POSITIVE LOGITS
    soever
    1.37
    pper
    1.11
    itz
    1.10
    itzer
    1.08
    ppers
    1.06
    ells
    0.98
    abouts
    0.96
    sth
    0.95
    leys
    0.95
    lers
    0.95
    Activations Density 0.093%

    No Known Activations