© 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. 3625
    Prev
    Next
    INDEX
    Explanations

    keywords and concepts related to coding and programming structures

    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
    0:0.11
    1:0.05
    2:0.04
    3:0.06
    4:0.04
    5:0.04
    6:0.21
    7:0.03
    8:0.02
    9:0.28
    10:0.03
    11:0.03
    Negative Logits
     Monarch
    -4.25
     Sands
    -3.95
     Aph
    -3.82
     toast
    -3.78
     Toast
    -3.69
     Titan
    -3.68
     Hipp
    -3.55
     Hendricks
    -3.52
     monarch
    -3.50
     Holland
    -3.41
    POSITIVE LOGITS
    File
    7.04
     File
    7.00
     file
    6.99
    file
    6.80
     files
    6.63
    Files
    6.20
    files
    6.20
     Files
    6.11
     FILE
    5.74
    FILE
    5.73
    Activations Density 0.010%

    No Known Activations