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

    Neuronpedia

    Jacobian LensNEW
    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. 893
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations, especially those related to social issues or rights advocacy

    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
    0:0.07
    1:0.01
    2:0.08
    3:0.45
    4:0.03
    5:0.11
    6:0.02
    7:0.04
    8:0.04
    9:0.02
    10:0.05
    11:0.03
    Negative Logits
     clocks
    -2.78
     brute
    -2.42
     guesses
    -2.41
     tricks
    -2.35
     fetch
    -2.32
     setups
    -2.32
     takeoff
    -2.31
     blows
    -2.31
     peaks
    -2.23
     diagrams
    -2.21
    POSITIVE LOGITS
     Association
    3.24
     Advoc
    3.14
     Coalition
    3.01
     Advisory
    2.97
     Partnership
    2.95
     Conserv
    2.92
     nonprofit
    2.89
     Foundation
    2.85
     Preservation
    2.84
     Lawyers
    2.81
    Activations Density 1.069%

    No Known Activations