© 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. 20696
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Thompson"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Thompson"

    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
    tes
    -0.86
    eas
    -0.85
    eer
    -0.84
    mble
    -0.79
    rator
    -0.78
    ter
    -0.77
    stract
    -0.77
    roach
    -0.77
    ãĤº
    -0.76
    lesi
    -0.76
    POSITIVE LOGITS
     Reuters
    1.01
     Browne
    0.86
     Gunn
    0.79
    sonian
    0.78
    psons
    0.75
     Chung
    0.71
    stown
    0.70
     Curry
    0.64
     Yor
    0.63
     Downing
    0.62
    Activations Density 0.061%

    No Known Activations