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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3320
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jane"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Jane."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orescent
    -0.89
    ctic
    -0.82
    fecture
    -0.81
    rophic
    -0.81
    ulative
    -0.79
    doors
    -0.79
    rophe
    -0.74
    ulatory
    -0.74
    */(
    -0.73
    igious
    -0.72
    POSITIVE LOGITS
     Jane
    1.27
     Doe
    1.19
    Jane
    1.12
     Leilan
    0.88
     Waters
    0.85
     Seymour
    0.81
     Rosenthal
    0.80
     Gad
    0.79
     Barton
    0.77
     Anne
    0.77
    Activations Density 0.007%

    No Known Activations