© 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. 10212
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast, opinion, or emotional reflections

    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
    0:0.24
    1:0.04
    2:0.08
    3:0.05
    4:0.04
    5:0.02
    6:0.12
    7:0.12
    8:0.02
    9:0.06
    10:0.11
    11:0.04
    Negative Logits
     Horton
    -3.51
     Nort
    -3.17
    Chicago
    -3.05
     Chicago
    -3.03
     Illinois
    -2.99
    ����
    -2.92
     LAT
    -2.90
     Fors
    -2.90
     STL
    -2.83
     Uzbek
    -2.80
    POSITIVE LOGITS
     Diana
    8.24
    iana
    4.03
     DD
    3.63
     Damian
    3.52
     Dion
    3.45
     Wonder
    3.39
     Alexandria
    3.33
     Dorothy
    3.31
     goddess
    3.23
     div
    3.22
    Activations Density 0.002%

    No Known Activations