© 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 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. 13610
    Prev
    Next
    INDEX
    Explanations

    URLs related to web pages and social media

    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
    0:0.10
    1:0.03
    2:0.08
    3:0.04
    4:0.07
    5:0.05
    6:0.27
    7:0.04
    8:0.06
    9:0.18
    10:0.02
    11:0.02
    Negative Logits
    ija
    -4.33
     Kon
    -4.29
     Yun
    -4.06
     Pyth
    -3.99
    Jon
    -3.95
     Rune
    -3.95
     bould
    -3.89
    stones
    -3.86
     Jon
    -3.71
     Klopp
    -3.65
    POSITIVE LOGITS
     carrier
    9.35
     Carrier
    9.12
     carriers
    8.77
     Hilton
    5.04
     airlines
    4.68
     airline
    4.49
     Sprint
    4.48
     LTE
    4.32
     CAR
    4.28
     passenger
    4.26
    Activations Density 0.004%

    No Known Activations