© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 606
    Prev
    Next
    INDEX
    Explanations

    terms related to penalties, especially in sports contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of penalties in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yll
    -0.91
    pocket
    -0.82
    atters
    -0.76
     Remastered
    -0.75
    need
    -0.72
    rina
    -0.72
    bian
    -0.72
    natureconservancy
    -0.71
    itect
    -0.71
     Emin
    -0.71
    POSITIVE LOGITS
     levied
    0.95
     penalty
    0.94
     imposed
    0.90
     penalties
    0.88
     leveled
    0.87
     incurred
    0.83
     inflicted
    0.77
     killers
    0.76
     knockout
    0.74
    udence
    0.73
    Activations Density 0.020%

    No Known Activations