© 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. 1-RES-JB
    11. 2160
    Prev
    Next
    INDEX
    Explanations

    mentions of the "FA Cup" in soccer-related contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular sports tournament, specifically the FA Cup

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Horton
    -0.73
    Trend
    -0.70
    atchewan
    -0.70
    ...]
    -0.68
    swing
    -0.67
    erous
    -0.65
    meyer
    -0.65
    come
    -0.64
    felt
    -0.64
    sets
    -0.63
    POSITIVE LOGITS
    FA
    0.95
    CLA
    0.89
    ITH
    0.89
     FA
    0.84
    IRE
    0.84
    uthor
    0.82
    KE
    0.82
    ruits
    0.79
    ILY
    0.78
    ILS
    0.78
    Activations Density 0.006%

    No Known Activations