© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2990
    Prev
    Next
    INDEX
    Explanations

    details or information specified in a statement or request

    oai_token-act-pair · gpt-3.5-turbo

    references to software products and their functionalities

    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
     Staten
    -0.80
     Boone
    -0.71
     Slate
    -0.71
    pmwiki
    -0.70
     longtime
    -0.68
    bably
    -0.67
     BuzzFeed
    -0.67
     Asheville
    -0.67
     Michaels
    -0.66
     Brooks
    -0.66
    POSITIVE LOGITS
     till
    1.36
    .(
    1.16
     irrespective
    1.16
    .
    1.12
    !.
    1.10
     !!
    1.07
     ðŁĻĤ
    1.07
     whereas
    1.06
    ".
    1.04
     whilst
    1.03
    Activations Density 1.016%

    No Known Activations