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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 19070
    Prev
    Next
    INDEX
    Explanations

    words related to discs or circular objects

    oai_token-act-pair · gpt-3.5-turbo

    references to "disc" and "disc golf."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aukee
    -0.78
    terday
    -0.70
    mberg
    -0.69
    atory
    -0.65
     Holmes
    -0.63
    HCR
    -0.61
     Werewolf
    -0.60
     masculinity
    -0.59
     Anim
    -0.59
     impunity
    -0.59
    POSITIVE LOGITS
    erning
    1.13
    ourses
    1.09
    ontent
    1.04
    rim
    1.02
    arding
    0.99
    washer
    0.96
    ussions
    0.95
    ursive
    0.95
    arbon
    0.95
    ounter
    0.93
    Activations Density 0.007%

    No Known Activations