© 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. 2-ATT-KK
    11. 16161
    Prev
    Next
    INDEX
    Explanations

    phrases related to media broadcasts and distribution

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.07
    1:0.03
    2:0.12
    3:0.09
    4:0.07
    5:0.07
    6:0.04
    7:0.03
    8:0.17
    9:0.14
    10:0.08
    11:0.04
    Negative Logits
     Ion
    -1.08
    iosis
    -1.07
    breeding
    -1.06
    akia
    -1.04
    agogue
    -1.00
    ongevity
    -1.00
     Galile
    -0.98
    eton
    -0.96
    abis
    -0.96
    eff
    -0.96
    POSITIVE LOGITS
    Quotes
    1.44
     television
    1.34
    CTV
    1.31
     TV
    1.30
    ebin
    1.26
     Television
    1.24
     Osw
    1.24
     Billboard
    1.23
    TV
    1.21
     Week
    1.16
    Activations Density 0.007%

    No Known Activations