© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 568
    Prev
    Next
    INDEX
    Explanations

    proper names starting with "Jay"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a particular individual named Jay

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

    No Comments

    Negative Logits
    htaking
    -0.84
    milo
    -0.79
    cffff
    -0.79
    osion
    -0.75
     stocking
    -0.73
    ancial
    -0.73
    iture
    -0.72
     sight
    -0.70
     foss
    -0.69
    bably
    -0.69
    POSITIVE LOGITS
    hawks
    1.15
    hawk
    1.09
    Jay
    1.06
     Jay
    0.97
    jay
    0.91
    walking
    0.88
    lon
    0.85
     Dee
    0.83
     Aj
    0.82
     Sek
    0.81
    Activations Density 0.008%

    No Known Activations