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. 0-RES-JB
    6. 17420
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a place or organization named "Circle."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific group or organization, particularly those associated with the term "Circle."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jen
    -0.85
    ded
    -0.75
     ethanol
    -0.68
     prop
    -0.63
     exhaust
    -0.63
     contr
    -0.63
     peanuts
    -0.62
    nia
    -0.61
     redist
    -0.59
     ashore
    -0.59
    POSITIVE LOGITS
     Circle
    4.21
    circle
    1.98
    Circ
    1.63
     circle
    1.55
     Cir
    1.52
     Square
    1.49
     Triangle
    1.34
     Circus
    1.19
     Crescent
    1.19
     Syndicate
    1.19
    Activations Density 0.014%

    No Known Activations