Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14517
    Prev
    Next
    INDEX
    Explanations

    quantitative metrics and statistics related to baseball performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.18
    1:0.06
    2:0.06
    3:0.06
    4:0.09
    5:0.04
    6:0.06
    7:0.10
    8:0.03
    9:0.06
    10:0.06
    11:0.15
    Negative Logits
    ë
    -3.16
    ovych
    -2.79
    rolet
    -2.78
    DragonMagazine
    -2.76
     Nebula
    -2.74
     Pets
    -2.66
     Dota
    -2.59
     resettlement
    -2.55
     indemn
    -2.52
     DAC
    -2.50
    POSITIVE LOGITS
     fastball
    5.54
     hitters
    4.68
     batters
    4.61
     cutter
    4.59
     pitches
    4.44
     Cutter
    4.35
     slider
    4.13
    Cub
    3.92
     Curve
    3.92
     pitchers
    3.79
    Activations Density 0.028%

    No Known Activations