© 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. 5932
    Prev
    Next
    INDEX
    Explanations

    interrogative sentences posing questions

    oai_token-act-pair · gpt-3.5-turbo

    questions and existential 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
    itches
    -0.70
    ventures
    -0.67
    "},"
    -0.65
    agues
    -0.61
    acan
    -0.58
    ibrary
    -0.57
    ussia
    -0.56
    apan
    -0.56
     parap
    -0.56
    ossip
    -0.55
    POSITIVE LOGITS
     whether
    1.37
     why
    1.21
     how
    1.16
     WHY
    1.11
    whether
    1.07
     what
    0.91
    why
    0.90
    :
    0.87
     HOW
    0.85
     posed
    0.85
    Activations Density 0.080%

    No Known Activations