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. 11-RES-JB
    6. 8664
    Prev
    Next
    INDEX
    Explanations

    sports-related keywords, focusing on football plays and game events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports plays and scoring events

    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
    icio
    -0.82
    enhagen
    -0.72
    bledon
    -0.69
     Nanto
    -0.68
    isodes
    -0.67
    ategor
    -0.65
    aeda
    -0.65
    netflix
    -0.64
    united
    -0.64
     ATP
    -0.63
    POSITIVE LOGITS
     touchdown
    1.34
     fumble
    1.34
     punt
    1.33
     kickoff
    1.29
     touchdowns
    1.19
     interception
    1.16
     quarterback
    1.12
     cornerback
    1.07
     Texans
    1.07
     receivers
    1.06
    Activations Density 0.291%

    No Known Activations