© 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. 9-ATT-KK
    11. 10243
    Prev
    Next
    INDEX
    Explanations

    instances of people speaking or quoting others in the text

    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
    2:0.05
    3:0.42
    4:0.08
    5:0.06
    6:0.03
    7:0.05
    8:0.06
    9:0.02
    10:0.06
    11:0.05
    Negative Logits
     airplanes
    -2.83
     armies
    -2.77
     automobiles
    -2.74
     codes
    -2.63
     fleets
    -2.56
     periods
    -2.55
     scams
    -2.55
     occasions
    -2.51
     ships
    -2.41
     purposes
    -2.39
    POSITIVE LOGITS
     negotiator
    3.18
    emaker
    3.11
     campaigner
    2.85
     spokeswoman
    2.78
    wright
    2.77
     staffer
    2.72
    director
    2.70
     adviser
    2.70
     Advocate
    2.69
     lawmaker
    2.69
    Activations Density 0.259%

    No Known Activations