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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 10441
    Prev
    Next
    INDEX
    Explanations

    keywords related to hockey leagues

    oai_token-act-pair · gpt-3.5-turbo

    references to hockey leagues and their abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Byrne
    -0.71
    ãĥ¯
    -0.70
     Gingrich
    -0.69
     Bedford
    -0.68
    combe
    -0.67
    behavior
    -0.65
    paper
    -0.61
     Spanish
    -0.61
    within
    -0.61
     Esp
    -0.60
    POSITIVE LOGITS
    HL
    1.28
    HF
    1.01
     rink
    0.98
     hockey
    0.95
    ockey
    0.90
    ipeg
    0.82
     goaltender
    0.80
     puck
    0.80
    SEA
    0.80
    uty
    0.79
    Activations Density 0.006%

    No Known Activations