© 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. 20767
    Prev
    Next
    INDEX
    Explanations

    mentions of the sports team "Tottenham Hotspur"

    oai_token-act-pair · gpt-3.5-turbo

    references to the football club Tottenham Hotspur

    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
    xon
    -0.90
    ppo
    -0.81
    cision
    -0.73
    lly
    -0.70
    carry
    -0.69
    phe
    -0.68
    paio
    -0.68
    opal
    -0.66
     Franken
    -0.66
     Scotia
    -0.64
    POSITIVE LOGITS
     Hots
    2.08
    rament
    0.87
     Rapids
    0.83
    fall
    0.83
    ites
    0.81
    kers
    0.75
    balls
    0.74
     Bros
    0.71
     unden
    0.71
     Tottenham
    0.71
    Activations Density 0.034%

    No Known Activations