© 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. 10-RES-JB
    11. 18821
    Prev
    Next
    INDEX
    Explanations

    proper nouns with titles or names

    oai_token-act-pair · gpt-3.5-turbo

    instances of ending punctuation

    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
    etheless
    -0.75
    wcs
    -0.72
     advis
    -0.70
     secondly
    -0.70
    translation
    -0.70
     charact
    -0.68
    ãĥĦ
    -0.64
     ignition
    -0.63
    ãĤ¨ãĥ«
    -0.63
     arrang
    -0.63
    POSITIVE LOGITS
     Smith
    1.03
     Olson
    1.00
     Miller
    1.00
     Baker
    1.00
     Bernstein
    0.99
     Stephens
    0.98
     Gors
    0.98
     Ware
    0.97
     Decker
    0.96
     Peterson
    0.96
    Activations Density 0.034%

    No Known Activations