© 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. 3-RES-JB
    11. 23358
    Prev
    Next
    INDEX
    Explanations

    references to the UEFA Champions League

    oai_token-act-pair · gpt-3.5-turbo

    references to the Champions League

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nu
    -0.78
    eral
    -0.76
    packing
    -0.73
    ward
    -0.72
    ITH
    -0.72
    opt
    -0.72
    employment
    -0.71
    vor
    -0.68
    WARD
    -0.68
    rolling
    -0.67
    POSITIVE LOGITS
     League
    1.12
    hip
    1.03
     Trophy
    0.97
     Champions
    0.91
     trophies
    0.83
    League
    0.80
    hips
    0.79
     strugg
    0.76
     Tournament
    0.76
     Champion
    0.76
    Activations Density 0.009%

    No Known Activations