© 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. 6-RES-JB
    11. 9550
    Prev
    Next
    INDEX
    Explanations

    titles or references to guides

    oai_token-act-pair · gpt-3.5-turbo

    titles and references to guides and FAQs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.79
     spect
    -0.71
    asted
    -0.70
    bley
    -0.69
     Klux
    -0.69
     concess
    -0.68
    etooth
    -0.68
    urrency
    -0.66
    yss
    -0.64
    ntil
    -0.64
    POSITIVE LOGITS
    book
    1.36
    books
    1.27
    posts
    1.10
    guide
    1.06
    BOOK
    0.99
     guide
    0.90
    tips
    0.84
     guides
    0.82
    cases
    0.80
     Guides
    0.80
    Activations Density 0.027%

    No Known Activations