© 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. 9-RES-JB
    11. 17084
    Prev
    Next
    INDEX
    Explanations

    references to the sport of rugby

    oai_token-act-pair · gpt-3.5-turbo

    mentions of rugby

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.87
    leneck
    -0.82
     Hoover
    -0.81
    insula
    -0.79
    igun
    -0.77
    iris
    -0.76
    roxy
    -0.74
    gur
    -0.74
    amaz
    -0.73
    ressive
    -0.72
    POSITIVE LOGITS
     league
    0.94
     union
    0.79
     Football
    0.77
     referees
    0.77
     League
    0.76
     rugby
    0.72
     Rugby
    0.71
    athan
    0.70
     feder
    0.68
     Premiership
    0.68
    Activations Density 0.033%

    No Known Activations