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. 16141
    Prev
    Next
    INDEX
    Explanations

    references to specific places or people named "Bre" or "Breeden"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Bre" and variations of it

    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
    ukong
    -0.68
    netflix
    -0.67
     dmg
    -0.66
    imura
    -0.65
    pixel
    -0.64
    etheless
    -0.63
    onymous
    -0.62
     addict
    -0.62
    asar
    -0.61
    ushi
    -0.61
    POSITIVE LOGITS
     Bre
    3.94
    Bre
    2.69
     BRE
    1.75
    bre
    1.61
     bre
    1.60
     Breed
    1.44
    BRE
    1.37
     Breaker
    1.21
     Bra
    1.15
     Ble
    1.06
    Activations Density 0.019%

    No Known Activations