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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 11-RES-JB
    6. 3170
    Prev
    Next
    INDEX
    Explanations

    mentions of college sports events

    oai_token-act-pair · gpt-3.5-turbo

    key points related to sports games and the outcomes associated with them

    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
    âĹ¼
    -0.89
     compr
    -0.82
    ãĤ¶
    -0.78
     droid
    -0.77
    ertodd
    -0.76
    zhen
    -0.75
    lav
    -0.73
    ancouver
    -0.71
    Alias
    -0.71
    Ñĭ
    -0.70
    POSITIVE LOGITS
     Heisman
    1.52
     NCAA
    1.52
     TCU
    1.46
     LSU
    1.43
     Clemson
    1.43
     Wildcats
    1.43
     BYU
    1.40
     Notre
    1.40
     Baylor
    1.39
     Purdue
    1.36
    Activations Density 0.932%

    No Known Activations