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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4458
    Prev
    Next
    INDEX
    Explanations

    text related to sports and team success

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    positive sentiments related to teamwork and success in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    pmwiki
    -0.86
     censored
    -0.83
     sinners
    -0.80
     vomit
    -0.77
     trope
    -0.76
     cens
    -0.76
     censor
    -0.74
    toggle
    -0.74
     ration
    -0.73
     lest
    -0.72
    POSITIVE LOGITS
    Coach
    1.15
     Coach
    1.08
     Soccer
    1.04
    Football
    1.04
     Rugby
    1.00
     Football
    1.00
     coaching
    0.99
     coached
    0.98
     AFL
    0.93
     Club
    0.92
    Activations Density 0.548%

    No Known Activations