© 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. 5-ATT-KK
    11. 43335
    Prev
    Next
    INDEX
    Explanations

    terms related to Kurdish military groups and their activities, particularly the YPG and Peshmerga forces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.01
    2:0.04
    3:0.04
    4:0.04
    5:0.04
    6:0.04
    7:0.03
    8:0.04
    9:0.08
    10:0.41
    11:0.13
    Negative Logits
    @@@@
    -1.67
    Haunted
    -1.64
     Ultron
    -1.60
     ADHD
    -1.57
     Atari
    -1.56
    iquid
    -1.50
    �
    -1.48
     iPod
    -1.47
    akespeare
    -1.47
    DoS
    -1.46
    POSITIVE LOGITS
     liberated
    1.60
     Patri
    1.56
     militia
    1.53
     sworn
    1.49
    athering
    1.48
     indigenous
    1.47
    ignty
    1.42
     leaders
    1.41
     traditionally
    1.38
     lands
    1.38
    Activations Density 0.026%

    No Known Activations