© 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 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. 10-RES-JB
    11. 3380
    Prev
    Next
    INDEX
    Explanations

    descriptions related to physical appearances

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors related to physical characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qqa
    -0.92
    Ô
    -0.89
    ascript
    -0.88
    cycles
    -0.86
    uden
    -0.85
    imum
    -0.85
    ancial
    -0.80
    imester
    -0.80
    soType
    -0.80
    wcs
    -0.79
    POSITIVE LOGITS
     teenager
    1.31
     Frenchman
    1.29
     youngster
    1.28
     businessman
    1.20
     narrator
    1.14
     protagonist
    1.14
     heroine
    1.11
     gentleman
    1.10
     politician
    1.08
     woman
    1.07
    Activations Density 0.229%

    No Known Activations