© 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. 11-RES-JB
    11. 3420
    Prev
    Next
    INDEX
    Explanations

    numbers mentioned within textual content

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities or extensive amounts of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odox
    -0.66
    allery
    -0.66
    bernatorial
    -0.63
     Slightly
    -0.63
     Moder
    -0.63
     Identified
    -0.63
    escription
    -0.62
    issan
    -0.62
    retty
    -0.60
    PN
    -0.59
    POSITIVE LOGITS
     crammed
    1.17
     vying
    1.09
     endlessly
    1.09
     countless
    1.08
     piled
    1.04
     annually
    1.03
     imaginable
    1.01
     every
    1.00
     untold
    0.99
     simultaneously
    0.99
    Activations Density 0.658%

    No Known Activations