© 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. 20096
    Prev
    Next
    INDEX
    Explanations

    names of companies, countries, and individuals

    oai_token-act-pair · gpt-3.5-turbo

    names and entities related to technology, politics, and consumer goods

    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
    witz
    -0.67
    olver
    -0.66
    lim
    -0.62
    luaj
    -0.61
    ãĥ¼ãĥĨãĤ£
    -0.59
     VIDE
    -0.58
    lopp
    -0.57
    kb
    -0.56
    20439
    -0.54
    izont
    -0.53
    POSITIVE LOGITS
     respectively
    0.90
     among
    0.74
     all
    0.70
     whatsoever
    0.67
     amongst
    0.67
     rounded
    0.65
     rounding
    0.65
    âĢ¦.
    0.64
    *.
    0.63
    âĢ¦
    0.63
    Activations Density 0.527%

    No Known Activations