© 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. 887
    Prev
    Next
    INDEX
    Explanations

    discussions about Colombian guerilla groups and their historical context

    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
    1:0.03
    2:0.07
    3:0.07
    4:0.04
    5:0.05
    6:0.08
    7:0.07
    8:0.32
    9:0.10
    10:0.03
    11:0.02
    Negative Logits
    ◼
    -3.38
    thodox
    -3.27
    Wisconsin
    -3.26
     Torah
    -3.20
     externalToEVAOnly
    -3.20
     Sabbath
    -3.18
    Michigan
    -3.17
     synagogue
    -3.15
     Wisconsin
    -3.10
     Wing
    -3.10
    POSITIVE LOGITS
     Colombian
    8.55
     Colombia
    8.21
     Colomb
    7.94
     Ecuador
    5.73
     Bolivia
    5.62
     Uruguay
    5.29
     cocaine
    5.18
     Santos
    5.17
     Paragu
    5.08
     Peru
    5.05
    Activations Density 0.014%

    No Known Activations