© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 12044
    Prev
    Next
    INDEX
    Explanations

    references to sports or game outcomes

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.14
    1:0.04
    2:0.16
    3:0.09
    4:0.11
    5:0.05
    6:0.05
    7:0.13
    8:0.03
    9:0.05
    10:0.05
    11:0.07
    Negative Logits
     Simpsons
    -2.88
     NASCAR
    -2.74
     SPORTS
    -2.61
    channelAvailability
    -2.58
    \\\\\\\\
    -2.51
     balloons
    -2.41
     ADS
    -2.40
    ixie
    -2.38
     DOT
    -2.35
     DOE
    -2.32
    POSITIVE LOGITS
    xc
    3.76
    xb
    3.74
    xd
    3.65
    xf
    3.41
     rook
    3.40
    xe
    3.33
    akov
    3.27
     Fn
    3.23
    ...]
    3.18
    xa
    3.15
    Activations Density 0.001%

    No Known Activations