© 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. 9-ATT-KK
    11. 7292
    Prev
    Next
    INDEX
    Explanations

    specific numeric values and details related to rankings and statistics

    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
    1:0.03
    2:0.06
    3:0.04
    4:0.05
    5:0.04
    6:0.18
    7:0.03
    8:0.05
    9:0.30
    10:0.03
    11:0.05
    Negative Logits
    amic
    -3.81
     Yamato
    -3.73
     Mubarak
    -3.63
    Bas
    -3.47
    Mp
    -3.44
    airo
    -3.38
     Yang
    -3.36
    Nap
    -3.31
     Simpsons
    -3.26
     Atl
    -3.26
    POSITIVE LOGITS
     WR
    8.31
     receivers
    7.75
     receiver
    7.29
    WR
    6.75
     Receiver
    6.34
     Rece
    5.47
     Conn
    4.55
     transmitter
    4.28
     receptions
    4.20
    ceiver
    4.15
    Activations Density 0.002%

    No Known Activations