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. 1-RES-JB
    6. 12343
    Prev
    Next
    INDEX
    Explanations

    phrases referencing specific sports seasons

    oai_token-act-pair · gpt-3.5-turbo

    references to sports seasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    merce
    -0.70
    plete
    -0.67
    imb
    -0.67
    ochet
    -0.66
     darn
    -0.65
    creen
    -0.64
     blazing
    -0.63
    HO
    -0.62
    pes
    -0.62
    NA
    -0.61
    POSITIVE LOGITS
    ãĥ¯ãĥ³
    0.95
    season
    0.90
    rawdownloadcloneembedreportprint
    0.81
    orsi
    0.72
     Afric
    0.72
    èĢħ
    0.72
    osterone
    0.72
     Nadu
    0.71
    DragonMagazine
    0.71
     Pagan
    0.70
    Activations Density 0.006%

    No Known Activations