© 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. 0-RES-JB
    11. 12747
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Dutton"

    oai_token-act-pair · gpt-3.5-turbo

    names associated with political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hello
    -0.74
     lights
    -0.66
     Cause
    -0.65
     hello
    -0.65
     hol
    -0.63
     Aer
    -0.63
     LEDs
    -0.63
     neighbors
    -0.62
     Meet
    -0.62
     hi
    -0.61
    POSITIVE LOGITS
    utton
    4.51
    utt
    1.24
    uton
    1.17
    utra
    1.15
    atton
    1.07
    urst
    1.04
     Sutton
    1.01
    uckland
    1.00
    utherland
    0.99
    weeney
    0.97
    Activations Density 0.017%

    No Known Activations