© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 12292
    Prev
    Next
    INDEX
    Explanations

    steps and instructions in cooking recipes

    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
    0:0.06
    1:0.04
    2:0.02
    3:0.15
    4:0.09
    5:0.12
    6:0.13
    7:0.08
    8:0.09
    9:0.12
    10:0.05
    11:0.01
    Negative Logits
     Lange
    -2.84
     Niagara
    -2.67
     Purg
    -2.58
    Miller
    -2.46
    pipe
    -2.44
     Coil
    -2.43
    Jake
    -2.39
    Lenin
    -2.38
     Messages
    -2.38
    Marie
    -2.36
    POSITIVE LOGITS
     avocado
    2.97
     chick
    2.70
     av
    2.67
     UA
    2.59
     EV
    2.56
     Afric
    2.48
    bleacher
    2.47
    ivas
    2.42
    abi
    2.31
     gar
    2.29
    Activations Density 0.008%

    No Known Activations