© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21702
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions related to terrorism and extremism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.05
    2:0.17
    3:0.09
    4:0.05
    5:0.08
    6:0.03
    7:0.04
    8:0.04
    9:0.25
    10:0.07
    11:0.03
    Negative Logits
    龍喚士
    -1.23
    OLD
    -1.20
    ritz
    -1.18
     curv
    -1.17
    ODY
    -1.17
    mallow
    -1.16
    cup
    -1.15
    APTER
    -1.14
    �
    -1.11
     Scrolls
    -1.10
    POSITIVE LOGITS
    abwe
    1.60
    aundering
    1.44
     Hezbollah
    1.44
    iferation
    1.41
    ��
    1.38
     Terrorism
    1.32
     Sabha
    1.32
     rampage
    1.31
     perpetrated
    1.27
     kidn
    1.25
    Activations Density 0.028%

    No Known Activations