© 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. 6-RES-JB
    11. 12768
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names, especially "Jane."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jane" in various contexts

    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
    orescent
    -0.91
    ctic
    -0.91
    */(
    -0.84
    idated
    -0.81
    rophe
    -0.79
    PDATE
    -0.78
    cffff
    -0.76
    akespe
    -0.75
    fecture
    -0.75
    ulative
    -0.73
    POSITIVE LOGITS
     Doe
    1.25
     Jane
    0.94
     Aust
    0.88
    Jane
    0.85
     Roe
    0.84
     Approximately
    0.84
     Jacobs
    0.82
     Seymour
    0.81
     Mayer
    0.80
    ju
    0.79
    Activations Density 0.016%

    No Known Activations