© 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. 7-RES-JB
    11. 1923
    Prev
    Next
    INDEX
    Explanations

    the names of sports teams or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations or teams

    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
    actionDate
    -0.71
    cribed
    -0.70
    redd
    -0.69
    tml
    -0.67
    omsky
    -0.67
    Bloomberg
    -0.65
    ãĥł
    -0.65
    clinton
    -0.65
    uminati
    -0.65
    inar
    -0.64
    POSITIVE LOGITS
     fans
    1.01
     goalkeeper
    0.94
     Stadium
    0.90
     midfield
    0.87
     Athletics
    0.86
     Fans
    0.85
     coach
    0.83
     players
    0.80
     sorely
    0.80
     keeper
    0.80
    Activations Density 0.155%

    No Known Activations