© 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. 11-RES-JB
    11. 710
    Prev
    Next
    INDEX
    Explanations

    phrases related to ice hockey, including player names, team names, and game situations

    oai_token-act-pair · gpt-3.5-turbo

    quotes or statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.89
    African
    -0.88
     plantation
    -0.86
    Egypt
    -0.85
     Nile
    -0.84
     plantations
    -0.81
     Kenyan
    -0.81
     Zimbabwe
    -0.81
     Liberia
    -0.80
     Osiris
    -0.79
    POSITIVE LOGITS
     NHL
    1.81
     Canadiens
    1.66
     Hockey
    1.65
     hockey
    1.63
     goaltender
    1.62
     puck
    1.62
     Penguins
    1.62
     AHL
    1.60
     Canucks
    1.57
     defenseman
    1.56
    Activations Density 0.822%

    No Known Activations