© 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. 10-RES-JB
    11. 3486
    Prev
    Next
    INDEX
    Explanations

    instances where the number "one" is emphasized or highlighted in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ooks
    -0.96
    efficients
    -0.88
    skirts
    -0.87
    ighters
    -0.86
    ourses
    -0.86
    acements
    -0.85
    ammers
    -0.85
    apons
    -0.84
    roots
    -0.84
    ributes
    -0.84
    POSITIVE LOGITS
     instance
    1.17
     person
    1.17
     hundred
    1.09
     thing
    1.06
     aspect
    1.03
     ounce
    0.96
     exception
    0.94
     element
    0.93
     iteration
    0.92
     facet
    0.91
    Activations Density 0.077%

    No Known Activations