© 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. 10-ATT-KK
    11. 7189
    Prev
    Next
    INDEX
    Explanations

    negative references to counter-terrorism actions and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    2:0.04
    3:0.05
    4:0.05
    5:0.04
    6:0.07
    7:0.05
    8:0.02
    9:0.30
    10:0.05
    11:0.20
    Negative Logits
     myself
    -2.56
     my
    -2.23
     separated
    -2.16
     ears
    -2.11
     distances
    -2.08
    gyn
    -2.07
     primaries
    -2.07
     captive
    -2.04
     Closed
    -2.04
     divorced
    -2.02
    POSITIVE LOGITS
     counter
    3.69
    counter
    3.63
     Counter
    3.47
    Counter
    3.30
    attack
    3.12
    offensive
    2.95
     countering
    2.93
    response
    2.75
    attacks
    2.74
     counters
    2.67
    Activations Density 0.005%

    No Known Activations