© 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. 7-RES-JB
    11. 4430
    Prev
    Next
    INDEX
    Explanations

    descriptions of events or actions in a sports context

    oai_token-act-pair · gpt-3.5-turbo

    instances of sports events and related actions occurring during games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oros
    -0.94
    osponsors
    -0.82
     specializing
    -0.75
    sonian
    -0.73
    coins
    -0.72
     additionally
    -0.72
    pots
    -0.71
    nostic
    -0.71
    CLUD
    -0.70
     specializes
    -0.70
    POSITIVE LOGITS
     halftime
    1.08
     teammate
    0.89
     locker
    0.87
     televised
    0.87
     Bulldogs
    0.84
     preseason
    0.81
     scrimmage
    0.81
     cheering
    0.78
     Sochi
    0.75
     moments
    0.75
    Activations Density 0.529%

    No Known Activations