Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 21900
    Prev
    Next
    INDEX
    Explanations

    names, particularly the name "Jane," in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jane."

    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
    orescent
    -0.90
    ctic
    -0.85
    */(
    -0.80
    cffff
    -0.78
    idated
    -0.77
    rophe
    -0.75
    rophic
    -0.74
    è¦ļéĨĴ
    -0.73
    ulum
    -0.73
    ulative
    -0.73
    POSITIVE LOGITS
     Doe
    1.25
     Jane
    1.02
    Jane
    0.90
     Approximately
    0.85
     Seymour
    0.80
     Aust
    0.80
     Jacobs
    0.80
    isons
    0.80
    ju
    0.79
     Roe
    0.77
    Activations Density 0.007%

    No Known Activations