© 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. 6135
    Prev
    Next
    INDEX
    Explanations

    questions posed using the phrase "Can you"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Can you" along with variations requesting action or information

    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
    ylum
    -0.69
    teen
    -0.67
    chwitz
    -0.66
    assic
    -0.66
    76561
    -0.64
    yk
    -0.63
    senal
    -0.63
     Lauder
    -0.62
    anamo
    -0.61
    gement
    -0.61
    POSITIVE LOGITS
     afford
    1.37
     imagine
    1.18
     possibly
    1.05
     quantify
    1.03
     realistically
    1.00
     please
    1.00
     foresee
    0.97
     PLEASE
    0.97
     feas
    0.97
     conceive
    0.96
    Activations Density 0.037%

    No Known Activations