© 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. 9-RES-JB
    11. 24283
    Prev
    Next
    INDEX
    Explanations

    leadership-related phrases, particularly in sports contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to leadership and performance statistics in sports

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    entric
    -0.74
    othy
    -0.64
     fundament
    -0.63
     address
    -0.58
    Address
    -0.56
     recons
    -0.56
    tein
    -0.56
     olds
    -0.56
    >[
    -0.55
    atari
    -0.55
    POSITIVE LOGITS
     scorer
    0.92
    better
    0.71
    interstitial
    0.70
     Runner
    0.69
    hunt
    0.69
    rush
    0.67
    ranked
    0.66
     rusher
    0.66
    ilyn
    0.66
    bare
    0.65
    Activations Density 0.051%

    No Known Activations