© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 35878
    Prev
    Next
    INDEX
    Explanations

    phrases related to hatred or incitement in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    3:0.06
    4:0.09
    5:0.02
    6:0.11
    7:0.38
    8:0.02
    9:0.04
    10:0.09
    11:0.06
    Negative Logits
     afford
    -1.65
    aceutical
    -1.48
    umerable
    -1.47
    ォ
    -1.42
     tether
    -1.40
    ourcing
    -1.38
     dear
    -1.35
     towed
    -1.34
    chester
    -1.34
     reconcil
    -1.34
    POSITIVE LOGITS
    inki
    1.79
    violence
    1.70
     sidx
    1.58
     hatred
    1.57
    aughs
    1.53
    azi
    1.53
    ichita
    1.50
     fires
    1.50
     violence
    1.48
     attack
    1.47
    Activations Density 0.001%

    No Known Activations