© 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. 0-RES-JB
    11. 12936
    Prev
    Next
    INDEX
    Explanations

    names of well-known brands or individuals, especially related to entertainment or sports

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names and brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atism
    -0.73
     mainland
    -0.73
    vern
    -0.72
    ÅŁ
    -0.71
    gly
    -0.70
     Eucl
    -0.69
    ern
    -0.69
     glyph
    -0.68
    aviour
    -0.68
    peria
    -0.67
    POSITIVE LOGITS
     Diesel
    3.33
     Decker
    1.86
    iesel
    1.79
     Cruise
    1.39
     induction
    1.30
     Mankind
    1.19
     Cumm
    1.08
     Michaels
    1.02
    inka
    0.96
     Swanson
    0.95
    Activations Density 0.068%

    No Known Activations