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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 3-RES-JB
    6. 1029
    Prev
    Next
    INDEX
    Explanations

    terms related to American football

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with sports terminology, particularly related to scrimmages and gameplay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olia
    -0.80
    aton
    -0.73
    sth
    -0.71
    ibel
    -0.69
     livest
    -0.67
    ora
    -0.66
     intest
    -0.66
    wig
    -0.65
     stale
    -0.65
    meal
    -0.64
    POSITIVE LOGITS
     scrimmage
    1.14
    halla
    0.95
    BACK
    0.83
    ONSORED
    0.82
    OUT
    0.80
    ãĤ§
    0.79
     Scouting
    0.79
    CLASSIFIED
    0.71
    Plex
    0.71
    æĺ
    0.69
    Activations Density 0.021%

    No Known Activations