© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 22797
    Prev
    Next
    INDEX
    Explanations

    critical events or decisions in sports or competitive contexts

    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
    0:0.07
    1:0.17
    2:0.05
    3:0.03
    4:0.03
    5:0.02
    6:0.20
    7:0.09
    8:0.02
    9:0.03
    10:0.20
    11:0.03
    Negative Logits
    elight
    -3.58
     Bald
    -2.91
     Gale
    -2.90
    apy
    -2.89
     lapt
    -2.85
     Lap
    -2.84
    uld
    -2.83
    azel
    -2.78
    tein
    -2.77
     Lur
    -2.75
    POSITIVE LOGITS
     Cons
    7.66
     cons
    6.95
     CONS
    6.76
    Cons
    6.41
    cons
    6.05
     Con
    4.43
     uncons
    4.33
     Pros
    4.04
     incons
    4.01
     recons
    3.63
    Activations Density 0.008%

    No Known Activations