© 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. 6-RES-JB
    11. 3615
    Prev
    Next
    INDEX
    Explanations

    mentions of hockey-related terms, especially focusing on actions related to the puck

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hockey gameplay and player positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quer
    -0.71
    atra
    -0.71
     GOODMAN
    -0.71
    ¿½
    -0.69
    iannopoulos
    -0.68
    bos
    -0.68
    aba
    -0.65
    ount
    -0.64
    Virgin
    -0.61
    ibility
    -0.61
    POSITIVE LOGITS
     rink
    1.01
    ipeg
    0.94
     defenseman
    0.89
     goalie
    0.80
     goaltender
    0.80
     hockey
    0.78
     NHL
    0.78
     goalt
    0.77
    sburgh
    0.76
     linem
    0.75
    Activations Density 0.093%

    No Known Activations