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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14792
    Prev
    Next
    INDEX
    Explanations

    negations and contentious actions in contexts involving conflict or protest

    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
    0:0.12
    1:0.12
    2:0.07
    3:0.07
    4:0.09
    5:0.01
    6:0.06
    7:0.16
    8:0.02
    9:0.03
    10:0.11
    11:0.09
    Negative Logits
    Angelo
    -2.57
    Vill
    -2.47
     Mods
    -2.38
    atts
    -2.35
     Undead
    -2.29
     Mald
    -2.27
    ドラ
    -2.27
     McK
    -2.21
    版
    -2.20
    ustain
    -2.19
    POSITIVE LOGITS
     tears
    4.44
     tear
    4.12
     weeping
    3.21
     Tears
    3.07
     rupture
    3.00
     weep
    2.94
     tearing
    2.84
     saliva
    2.70
     sob
    2.67
     crying
    2.61
    Activations Density 0.003%

    No Known Activations