© 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. 21562
    Prev
    Next
    INDEX
    Explanations

    phrases related to power dynamics and authority

    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
    1:0.02
    2:0.16
    3:0.05
    4:0.30
    5:0.07
    6:0.03
    7:0.02
    8:0.04
    9:0.13
    10:0.06
    11:0.02
    Negative Logits
    govtrack
    -1.58
    rants
    -1.48
    Sense
    -1.45
    Street
    -1.38
    bush
    -1.35
     Frazier
    -1.34
    ��
    -1.31
     Scores
    -1.30
    Stars
    -1.30
    Week
    -1.29
    POSITIVE LOGITS
     deduction
    1.50
    ifice
    1.48
     inflicting
    1.43
     patriarchy
    1.42
     constructing
    1.42
     afterlife
    1.38
     civilization
    1.38
     degrade
    1.37
    ifter
    1.37
     reconciliation
    1.34
    Activations Density 0.016%

    No Known Activations