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. 7-RES-JB
    6. 3381
    Prev
    Next
    INDEX
    Explanations

    references to professional sports, athletes, and teams

    oai_token-act-pair · gpt-3.5-turbo

    sports-related terminology and player statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DCS
    -0.70
    Ħ¢
    -0.64
     civilisation
    -0.62
    ãĢı
    -0.60
     lifestyles
    -0.58
     attRot
    -0.58
    Rew
    -0.56
    ifestyle
    -0.55
    IDENT
    -0.55
    =-=-=-=-=-=-=-=-
    -0.53
    POSITIVE LOGITS
     likewise
    0.85
     similarly
    0.79
    adj
    0.67
    onite
    0.66
     meanwhile
    0.64
    reditary
    0.62
    oother
    0.59
    trak
    0.57
    osuke
    0.57
     folded
    0.56
    Activations Density 1.298%

    No Known Activations