© 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. 7640
    Prev
    Next
    INDEX
    Explanations

    references to specific reality TV show participants and the emotions or events surrounding them

    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
    0:0.25
    1:0.04
    2:0.05
    3:0.07
    4:0.08
    5:0.03
    6:0.18
    7:0.06
    8:0.03
    9:0.05
    10:0.08
    11:0.03
    Negative Logits
     Minotaur
    -3.55
    umbledore
    -3.52
    cens
    -3.38
     Galile
    -3.34
     Riy
    -3.31
     Tibet
    -3.31
     col
    -3.30
     Classification
    -3.27
     yuan
    -3.23
     Scholar
    -3.23
    POSITIVE LOGITS
    wives
    5.58
    RH
    5.44
     RH
    5.42
     Vander
    4.20
     Bravo
    4.09
     Vick
    3.86
     Wedding
    3.78
     Pam
    3.65
     Teresa
    3.63
     Ashley
    3.60
    Activations Density 0.002%

    No Known Activations