Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 19123
    Prev
    Next
    INDEX
    Explanations

    words related to hockey leagues and player statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to hockey leagues and their associated metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.93
    sth
    -0.87
    bart
    -0.78
    cia
    -0.78
    ãĥķ
    -0.76
    math
    -0.76
    efully
    -0.75
    anamo
    -0.75
    cli
    -0.75
    oeuv
    -0.75
    POSITIVE LOGITS
     playoffs
    1.04
     Championship
    0.96
     championship
    0.96
     Playoffs
    0.93
     standings
    0.91
     championships
    0.90
     Rookie
    0.88
     qualifiers
    0.88
     Tournament
    0.87
     Playoff
    0.85
    Activations Density 0.128%

    No Known Activations