© 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. 9-ATT-KK
    11. 20596
    Prev
    Next
    INDEX
    Explanations

    quantitative indicators related to legislation and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.02
    2:0.08
    3:0.09
    4:0.03
    5:0.05
    6:0.06
    7:0.43
    8:0.03
    9:0.03
    10:0.07
    11:0.02
    Negative Logits
    ��
    -3.24
     Alive
    -3.04
    20439
    -3.03
    Luck
    -2.74
     suffice
    -2.69
    wikipedia
    -2.65
    Answer
    -2.58
    upuncture
    -2.52
    reetings
    -2.51
    dayName
    -2.50
    POSITIVE LOGITS
     unhealthy
    4.22
     harmful
    4.12
     nasty
    3.94
     destructive
    3.91
     ugly
    3.82
     detrimental
    3.77
     bad
    3.75
     vicious
    3.64
     disastrous
    3.58
     hostility
    3.57
    Activations Density 0.226%

    No Known Activations