© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5077
    Prev
    Next
    INDEX
    Explanations

    stats and percentages related to basketball, specifically focusing on shooting and scoring efficiency

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    statistical references and numerical data related to scoring in basketball

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    interstitial
    -0.83
    croft
    -0.81
    bart
    -0.77
    bang
    -0.76
    pins
    -0.73
    clamation
    -0.72
    cuts
    -0.70
    andon
    -0.70
    byn
    -0.68
    Reviewer
    -0.68
    POSITIVE LOGITS
    iries
    0.64
     airspace
    0.59
    oir
    0.56
     stance
    0.56
    oleon
    0.55
     preferences
    0.55
     familiarity
    0.55
    ile
    0.54
    ales
    0.54
    ItemThumbnailImage
    0.54
    Activations Density 0.130%

    No Known Activations