© 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. 0-RES-JB
    11. 16518
    Prev
    Next
    INDEX
    Explanations

    phrases related to the famous tennis tournament Wimbledon

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cassidy
    -0.74
     insurance
    -0.66
     carriers
    -0.64
     helmet
    -0.64
     shield
    -0.64
     enrollment
    -0.62
     Pact
    -0.61
     Ï
    -0.60
    cast
    -0.60
    alyses
    -0.60
    POSITIVE LOGITS
     Wim
    4.36
     Notting
    1.28
     tennis
    1.19
     Tennis
    1.16
     Wembley
    1.15
     Wag
    1.12
     Wem
    1.12
    bledon
    1.09
     Frie
    1.08
     Johannes
    1.06
    Activations Density 0.024%

    No Known Activations