© 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. 11-RES-JB
    11. 13378
    Prev
    Next
    INDEX
    Explanations

    time schedules and stages of a competition or tournament

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to competitive events and tournaments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    dylib
    -1.00
    gur
    -0.84
    uti
    -0.78
    irrel
    -0.74
    framework
    -0.72
    cia
    -0.70
     Anon
    -0.69
    etsy
    -0.69
    baugh
    -0.69
    abulary
    -0.67
    POSITIVE LOGITS
     semifinals
    1.45
     Finals
    1.27
     Winners
    1.26
     finals
    1.23
     tournament
    1.23
     loser
    1.23
     Rounds
    1.22
     Tournament
    1.22
     Playoffs
    1.20
     seeded
    1.19
    Activations Density 0.210%

    No Known Activations