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. 8023
    Prev
    Next
    INDEX
    Explanations

    references to the location "Wimbledon"

    oai_token-act-pair · gpt-3.5-turbo

    references to significant locations and names

    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
    ONSORED
    -0.67
    pedia
    -0.66
     inherit
    -0.65
    HM
    -0.64
    ifer
    -0.64
    Reviewer
    -0.63
     Kass
    -0.63
    ebook
    -0.63
    toggle
    -0.62
     steering
    -0.62
    POSITIVE LOGITS
     Aires
    0.97
     Lumpur
    0.92
     mosqu
    0.83
    aeper
    0.79
    terness
    0.78
    orius
    0.77
    apolis
    0.76
     Prix
    0.76
     corrid
    0.75
    oria
    0.74
    Activations Density 0.017%

    No Known Activations