© 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. 9254
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual, particularly related to job and employment context

    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
    0:0.13
    1:0.16
    2:0.10
    3:0.04
    4:0.03
    5:0.02
    6:0.11
    7:0.11
    8:0.02
    9:0.06
    10:0.15
    11:0.03
    Negative Logits
     Io
    -3.15
     Tuc
    -2.95
    atos
    -2.90
    alore
    -2.80
     Tir
    -2.73
     Il
    -2.69
    izza
    -2.64
     Albania
    -2.62
     Lic
    -2.60
    Lic
    -2.59
    POSITIVE LOGITS
     Whitney
    7.87
    Whit
    5.52
     Whit
    3.57
     Whitman
    3.32
    BuyableInstoreAndOnline
    3.19
     Jenner
    2.92
     liner
    2.90
     Wallace
    2.87
     Upton
    2.79
     Kardashian
    2.72
    Activations Density 0.001%

    No Known Activations