© 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. 13623
    Prev
    Next
    INDEX
    Explanations

    references to sports teams, particularly the Washington Redskins

    oai_token-act-pair · gpt-3.5-turbo

    references to the Washington Redskins football team and related players

    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
    isf
    -0.86
    irlf
    -0.81
    uckland
    -0.74
    ements
    -0.73
    edged
    -0.73
    tif
    -0.73
     newsp
    -0.70
     Edinburgh
    -0.69
    utic
    -0.69
    stroke
    -0.68
    POSITIVE LOGITS
     linebacker
    1.02
     Broncos
    0.99
     quarterback
    0.97
     Manziel
    0.96
     Redskins
    0.96
     Seahawks
    0.94
     Jaguars
    0.94
     cornerback
    0.92
     linebackers
    0.92
     QB
    0.92
    Activations Density 0.185%

    No Known Activations