© 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. 1-RES-JB
    11. 20723
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of ice hockey goalies

    oai_token-act-pair · gpt-3.5-turbo

    references to goalies in a sports context

    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
    Sax
    -0.73
    INGS
    -0.68
    hips
    -0.68
    au
    -0.67
    ardy
    -0.67
    heid
    -0.67
    ings
    -0.66
    hare
    -0.66
    omething
    -0.65
    ombat
    -0.64
    POSITIVE LOGITS
     goalie
    1.26
     goaltender
    1.17
     goalkeeper
    0.96
     goalt
    0.90
     catcher
    0.75
     defenseman
    0.74
     kicker
    0.72
     Petr
    0.70
     keeper
    0.67
     Adin
    0.65
    Activations Density 0.011%

    No Known Activations