© 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. 10-ATT-KK
    11. 15020
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial institutions and investment dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.15
    1:0.07
    2:0.10
    3:0.06
    4:0.05
    5:0.02
    6:0.14
    7:0.10
    8:0.04
    9:0.04
    10:0.12
    11:0.06
    Negative Logits
    ł
    -3.02
    �
    -2.96
    ć
    -2.81
    odi
    -2.76
     Handler
    -2.67
    É
    -2.54
    Hop
    -2.36
    Lew
    -2.35
    oodle
    -2.32
    ˜
    -2.29
    POSITIVE LOGITS
     Vanguard
    8.71
     Squadron
    4.80
     Valkyrie
    4.67
    anguard
    4.19
     Vigil
    4.07
     Valhalla
    3.95
     Vega
    3.90
     Vortex
    3.68
     squadron
    3.67
     Avenger
    3.56
    Activations Density 0.002%

    No Known Activations