© 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. 11-RES-JB
    11. 21360
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports, specifically actions and scenes on the sports fields, courts, or ice

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports and athletic activities, particularly those involving fields and ice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oras
    -0.70
    netflix
    -0.69
    ë
    -0.66
     Primordial
    -0.66
     warr
    -0.63
     Catalog
    -0.62
     Telesc
    -0.62
     href
    -0.60
    ĸ
    -0.59
     Webs
    -0.58
    POSITIVE LOGITS
     podium
    0.78
    keepers
    0.77
     scoreboard
    0.77
    washer
    0.75
     antics
    0.75
     cheering
    0.73
     benches
    0.73
     floor
    0.72
     brawl
    0.72
    plays
    0.71
    Activations Density 0.165%

    No Known Activations