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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10006
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Tart"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific characters or elements in narratives, particularly involving the word "tart."

    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
    ardless
    -0.87
    rals
    -0.77
    port
    -0.77
    builders
    -0.75
    ports
    -0.73
    icide
    -0.71
    ulative
    -0.70
    enhagen
    -0.70
    borg
    -0.70
    meet
    -0.69
    POSITIVE LOGITS
     Tart
    0.87
    displayText
    0.86
    umen
    0.69
     GOODMAN
    0.67
     Kou
    0.66
    DonaldTrump
    0.66
     Iz
    0.63
     Gou
    0.63
    LD
    0.62
     Acad
    0.61
    Activations Density 0.019%

    No Known Activations