© 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. 8-RES-JB
    11. 1167
    Prev
    Next
    INDEX
    Explanations

    mentions of words starting with "Tr"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific subject or entity identified by the token "Tr."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yeast
    -0.73
     Mechdragon
    -0.69
    ELS
    -0.68
    WARE
    -0.67
     arts
    -0.67
     tong
    -0.65
     writ
    -0.65
    âĸ¬âĸ¬
    -0.65
     minded
    -0.65
    lihood
    -0.64
    POSITIVE LOGITS
    acer
    1.28
    ainer
    1.26
    ained
    1.23
    unks
    1.23
    istan
    1.21
    icol
    1.20
    umps
    1.20
    ains
    1.18
    agic
    1.16
    icky
    1.14
    Activations Density 0.017%

    No Known Activations