© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15506
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to managerial roles or actions

    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
    0:0.22
    1:0.05
    2:0.03
    3:0.10
    4:0.04
    5:0.03
    6:0.07
    7:0.15
    8:0.02
    9:0.06
    10:0.15
    11:0.03
    Negative Logits
     Azerbai
    -3.41
     Afghan
    -3.12
    oglu
    -3.11
    Turkish
    -3.07
     Cherokee
    -3.02
     Kazakh
    -2.90
    Pakistan
    -2.87
    zai
    -2.85
     Pakistani
    -2.83
     Afgh
    -2.82
    POSITIVE LOGITS
     Southampton
    6.80
     Saints
    6.10
    ampton
    5.10
     Plymouth
    3.67
     Leicester
    3.35
     Norwich
    3.33
     Worcester
    3.22
     Portsmouth
    3.21
     Brees
    3.18
     Lambert
    3.16
    Activations Density 0.001%

    No Known Activations