© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14241
    Prev
    Next
    INDEX
    Explanations

    claims related to terrorism and counter-terrorism narratives

    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
    0:0.20
    1:0.14
    2:0.08
    3:0.05
    4:0.03
    5:0.02
    6:0.05
    7:0.08
    8:0.02
    9:0.03
    10:0.21
    11:0.04
    Negative Logits
    antine
    -4.01
    cius
    -3.81
    RH
    -3.07
     Alc
    -2.98
     aph
    -2.95
    drivers
    -2.95
    ragon
    -2.92
     CIS
    -2.88
     Atlas
    -2.81
     Borg
    -2.79
    POSITIVE LOGITS
     Sho
    10.76
     sho
    5.96
     Sha
    5.41
     Shant
    5.03
     Ko
    4.35
    Sh
    4.11
     Shu
    3.96
     Bahá
    3.93
    sha
    3.88
     Poo
    3.85
    Activations Density 0.002%

    No Known Activations