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

    Neuronpedia

    Jacobian LensNEW
    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. 4864
    Prev
    Next
    INDEX
    Explanations

    words related to sports journalism and media coverage

    oai_token-act-pair · gpt-3.5-turbo

    mentions of sports media entities and networks

    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
    byn
    -1.02
    bara
    -0.85
    ertodd
    -0.84
    Lib
    -0.84
    debian
    -0.80
    wikipedia
    -0.79
    etsy
    -0.76
    duino
    -0.76
    ndra
    -0.75
    olen
    -0.75
    POSITIVE LOGITS
     leagues
    1.15
     Sports
    1.00
     Sport
    0.99
     announ
    0.98
     SPORTS
    0.97
     league
    0.96
     scouting
    0.95
     ESPN
    0.95
    ESPN
    0.95
     announcer
    0.93
    Activations Density 0.172%

    No Known Activations