© 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. 20905
    Prev
    Next
    INDEX
    Explanations

    phrases related to cleaning or tidying up

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to cleaning or correcting past mistakes

    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
    enza
    -0.75
    yip
    -0.73
    nostic
    -0.73
    ratulations
    -0.72
    isSpecialOrderable
    -0.71
    nir
    -0.67
    ĸļ
    -0.66
    ait
    -0.64
    option
    -0.64
     pairing
    -0.64
    POSITIVE LOGITS
     polluted
    1.04
     dishes
    1.03
     toilets
    1.02
     mess
    1.00
     wounds
    0.96
     stains
    0.94
     spills
    0.91
     floors
    0.88
     ruins
    0.86
     contaminated
    0.84
    Activations Density 0.112%

    No Known Activations