© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 5004
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to sports tournaments

    oai_token-act-pair · gpt-3.5-turbo

    references to various sports championships and competitions

    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
    ily
    -0.75
     labor
    -0.71
     sett
    -0.67
    NPR
    -0.67
    zos
    -0.66
     forg
    -0.65
     implicit
    -0.65
    metic
    -0.65
    tis
    -0.64
     nanop
    -0.62
    POSITIVE LOGITS
     Championship
    3.59
     Championships
    2.40
     championship
    2.03
     championships
    1.65
     Champion
    1.57
     Premiership
    1.56
     Champions
    1.44
     Tournament
    1.44
     Finals
    1.33
    ampions
    1.25
    Activations Density 0.013%

    No Known Activations