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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13382
    Prev
    Next
    INDEX
    Explanations

    references to sports events, achievements, and statistics, especially related to championships like the Stanley Cup and the Super Bowl

    oai_token-act-pair · gpt-3.5-turbo

    references to major sports events and competitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nsic
    -0.78
     vigil
    -0.76
    oeuv
    -0.73
    terday
    -0.73
    respond
    -0.70
     beh
    -0.69
    irit
    -0.69
    cul
    -0.68
    metic
    -0.68
    ksh
    -0.67
    POSITIVE LOGITS
     Rookie
    1.25
     Playoff
    1.20
     playoffs
    1.19
     Finals
    1.18
     Playoffs
    1.18
     playoff
    1.12
    League
    1.12
     Championship
    1.11
     postseason
    1.09
     standings
    1.08
    Activations Density 0.122%

    No Known Activations