© 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. 21967
    Prev
    Next
    INDEX
    Explanations

    mentions or variations of the term "pe" which seem to be artifacts or inaccuracies in the data

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "peat."

    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
    schild
    -0.76
    enegger
    -0.73
    SHIP
    -0.71
    worthy
    -0.68
     guiActiveUnfocused
    -0.67
    picture
    -0.66
     GOODMAN
    -0.66
     EDITION
    -0.65
     Pulse
    -0.65
    footed
    -0.63
    POSITIVE LOGITS
    ggy
    1.03
    asant
    0.99
    pperc
    0.97
    gging
    0.96
    eps
    0.95
    eper
    0.95
    eking
    0.94
    aking
    0.92
    achy
    0.89
    ipe
    0.89
    Activations Density 0.009%

    No Known Activations