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. 22716
    Prev
    Next
    INDEX
    Explanations

    years related to sports seasons

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years and sports-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
    upon
    -0.73
    ifles
    -0.69
    rapnel
    -0.67
    oxide
    -0.66
    SPONSORED
    -0.66
    dain
    -0.65
    rily
    -0.64
    wright
    -0.64
    edly
    -0.64
    andering
    -0.62
    POSITIVE LOGITS
     edition
    1.15
     Olympics
    1.11
     calendar
    0.98
     season
    0.96
     Winter
    0.95
     Olympic
    0.90
     Sochi
    0.87
     playoffs
    0.86
     iteration
    0.86
     Oscars
    0.83
    Activations Density 0.089%

    No Known Activations