© 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. 6-RES-JB
    11. 14699
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names like "Gary"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Gary"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    semble
    -0.76
    xual
    -0.76
    enegger
    -0.73
    uality
    -0.71
    ĺħ
    -0.71
    joined
    -0.71
    ilation
    -0.68
    orship
    -0.68
    ylum
    -0.67
    itect
    -0.67
    POSITIVE LOGITS
     Johnson
    0.97
     Neville
    0.90
     Cooper
    0.89
     Sheffield
    0.86
     Hir
    0.81
     Melvin
    0.80
     Becker
    0.78
     Cohn
    0.77
     Kub
    0.76
     Gy
    0.76
    Activations Density 0.013%

    No Known Activations