© 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. 6854
    Prev
    Next
    INDEX
    Explanations

    instances of incidents and experiences related to sports, emphasizing both personal and team narratives

    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
    0:0.20
    1:0.06
    2:0.08
    3:0.05
    4:0.05
    5:0.04
    6:0.07
    7:0.09
    8:0.04
    9:0.02
    10:0.18
    11:0.08
    Negative Logits
     Motorola
    -2.94
    uclear
    -2.87
     iodine
    -2.85
     phosphorus
    -2.73
     plutonium
    -2.66
     foreskin
    -2.65
     SPI
    -2.64
    Pol
    -2.60
     Iw
    -2.54
     mathemat
    -2.54
    POSITIVE LOGITS
     Cab
    9.17
     cab
    6.96
     Carr
    4.82
     Sau
    4.47
     Taxi
    4.07
     Cam
    4.06
     taxi
    4.01
     Qué
    3.69
     Paddock
    3.60
     Cabin
    3.59
    Activations Density 0.005%

    No Known Activations