© 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. 20587
    Prev
    Next
    INDEX
    Explanations

    elements related to descriptions and performances in films

    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
    0:0.26
    1:0.06
    2:0.10
    3:0.05
    4:0.05
    5:0.03
    6:0.08
    7:0.08
    8:0.03
    9:0.05
    10:0.10
    11:0.07
    Negative Logits
     Kardashian
    -3.54
     Kardash
    -3.46
     issu
    -3.34
     basketball
    -3.32
     Rih
    -3.26
     leptin
    -3.23
    Jenn
    -3.20
     gol
    -3.19
     TAG
    -3.18
     Boko
    -3.12
    POSITIVE LOGITS
     Carpenter
    9.90
     Briggs
    5.04
     Percy
    4.13
     Lovecraft
    4.09
     Hawth
    4.00
     Cthulhu
    3.75
     Petersen
    3.65
     Thornton
    3.63
     Coleman
    3.55
     coffin
    3.52
    Activations Density 0.001%

    No Known Activations