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. 10-RES-JB
    6. 18159
    Prev
    Next
    INDEX
    Explanations

    information about Olympic events and details about participants

    oai_token-act-pair · gpt-3.5-turbo

    references to the Olympic Games and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     voic
    -0.89
     foreclosure
    -0.85
    Dispatch
    -0.84
     rm
    -0.84
     Ezra
    -0.82
    Chuck
    -0.81
    mons
    -0.80
    âĹ¼
    -0.76
    umblr
    -0.76
     Dispatch
    -0.75
    POSITIVE LOGITS
     Olympic
    1.73
     Olympics
    1.70
     IOC
    1.68
     Sochi
    1.61
     Paraly
    1.55
     Olymp
    1.54
     Fifa
    1.50
     medal
    1.46
     FIFA
    1.46
     medals
    1.40
    Activations Density 0.461%

    No Known Activations