© 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. 9-ATT-KK
    11. 6634
    Prev
    Next
    INDEX
    Explanations

    content related to casual conversation or discourse markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.02
    2:0.07
    3:0.03
    4:0.05
    5:0.04
    6:0.26
    7:0.05
    8:0.10
    9:0.21
    10:0.02
    11:0.03
    Negative Logits
     Rico
    -4.34
     Volcano
    -3.79
     Jaguar
    -3.56
    ulent
    -3.48
     Salam
    -3.45
     Suns
    -3.38
     lamps
    -3.35
     tablet
    -3.33
     tablets
    -3.31
     Staten
    -3.31
    POSITIVE LOGITS
     Bre
    9.64
    Bre
    8.80
    bre
    6.92
     bre
    6.87
     BRE
    6.66
     Breed
    6.10
    BRE
    4.92
     Kre
    4.54
    breeding
    4.45
     Breitbart
    4.04
    Activations Density 0.003%

    No Known Activations