© 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. 9-RES-JB
    11. 11333
    Prev
    Next
    INDEX
    Explanations

    words related to specific names or titles, especially with the prefix "Pr"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "Pr" followed by various letters or words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.71
     Wonderland
    -0.64
    romeda
    -0.61
    REM
    -0.61
    DIR
    -0.59
    apego
    -0.59
    Reloaded
    -0.58
     Urug
    -0.57
    thumbnails
    -0.56
    Ñı
    -0.56
    POSITIVE LOGITS
    ciples
    1.19
    cipled
    1.08
    cess
    0.84
    bably
    0.80
    fecture
    0.71
    itte
    0.71
    ety
    0.70
    ļéĨĴ
    0.66
    eline
    0.65
    heed
    0.64
    Activations Density 0.069%

    No Known Activations