© 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. 9571
    Prev
    Next
    INDEX
    Explanations

    specific references to television channels and services

    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
    0:0.28
    1:0.03
    2:0.11
    3:0.10
    4:0.03
    5:0.01
    6:0.09
    7:0.10
    8:0.01
    9:0.03
    10:0.06
    11:0.08
    Negative Logits
     horns
    -3.24
     Bav
    -3.08
     Kabul
    -3.00
     Brewer
    -2.92
     Mead
    -2.89
     goats
    -2.88
     Harley
    -2.87
     Thieves
    -2.87
    jah
    -2.86
    phi
    -2.84
    POSITIVE LOGITS
     TV
    7.46
     TVs
    7.26
     Roku
    6.90
     telev
    6.83
    TV
    6.80
     Television
    6.74
     television
    6.68
    levision
    6.61
     tv
    6.59
     broadcasters
    6.06
    Activations Density 0.227%

    No Known Activations