© 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. 4-RES-JB
    11. 10548
    Prev
    Next
    INDEX
    Explanations

    dates mentioned in the format "Month.Day."

    oai_token-act-pair · gpt-3.5-turbo

    sentences that begin with a period and signify the end of a thought or statement

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

    No Comments

    Negative Logits
    ert
    -0.69
     transact
    -0.66
     inver
    -0.65
     minded
    -0.64
     chimpanzees
    -0.63
    rett
    -0.63
     trophies
    -0.63
     outstanding
    -0.62
     prin
    -0.62
     cradle
    -0.61
    POSITIVE LOGITS
     Accessed
    0.79
    sbm
    0.79
     Macedonia
    0.78
     Madness
    0.77
    assetsadobe
    0.75
    Downloadha
    0.72
     Afterwards
    0.68
     Garrison
    0.67
     Surge
    0.67
     Huss
    0.66
    Activations Density 0.041%

    No Known Activations