© 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. 10-RES-JB
    11. 4144
    Prev
    Next
    INDEX
    Explanations

    sports-related terms, specifically related to games

    oai_token-act-pair · gpt-3.5-turbo
    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
    aft
    -0.66
    LECT
    -0.61
    sie
    -0.60
     Refugees
    -0.60
    hai
    -0.60
    istani
    -0.60
    ingen
    -0.59
    orship
    -0.58
    Adds
    -0.57
    azon
    -0.57
    POSITIVE LOGITS
    plan
    1.02
    manship
    0.90
     against
    0.86
    keepers
    0.84
    winning
    0.83
    day
    0.82
    keeper
    0.82
    PLAY
    0.81
     played
    0.77
     Played
    0.77
    Activations Density 0.066%

    No Known Activations