© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 17245
    Prev
    Next
    INDEX
    Explanations

    mentions of sports events such as quarterfinals and semifinals

    oai_token-act-pair · gpt-3.5-turbo

    references to sports matches, specifically finals and semifinals

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

    No Comments

    Negative Logits
    relative
    -0.70
     welf
    -0.68
    heter
    -0.65
    bench
    -0.65
    station
    -0.63
    same
    -0.61
    whe
    -0.61
    Station
    -0.60
     impe
    -0.60
     ageing
    -0.60
    POSITIVE LOGITS
    naire
    0.92
    finals
    0.89
     finals
    0.89
    iership
    0.88
    iminary
    0.84
     Finals
    0.84
     Playoffs
    0.83
     semifinals
    0.80
    ifiers
    0.77
    final
    0.77
    Activations Density 0.029%

    No Known Activations