© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15666
    Prev
    Next
    INDEX
    Explanations

    words related to the "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 @ 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
    nu
    -0.79
    tracks
    -0.79
    orders
    -0.79
    WARD
    -0.76
    sil
    -0.75
    packing
    -0.72
    shore
    -0.72
    til
    -0.71
    eral
    -0.71
     Canaver
    -0.71
    POSITIVE LOGITS
     League
    1.21
     Trophy
    1.04
    League
    0.90
     Cup
    0.89
     Champions
    0.82
     strugg
    0.82
    hip
    0.81
     XI
    0.78
     league
    0.78
     Cups
    0.77
    Activations Density 0.017%

    No Known Activations