© 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. 6982
    Prev
    Next
    INDEX
    Explanations

    concepts related to the behavior and interaction of electrons in physical systems

    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
    0:0.18
    1:0.07
    2:0.07
    3:0.05
    4:0.06
    5:0.03
    6:0.06
    7:0.19
    8:0.03
    9:0.04
    10:0.09
    11:0.08
    Negative Logits
     Scare
    -2.73
     Mandal
    -2.73
     Cth
    -2.54
     SDK
    -2.51
    quist
    -2.48
     Holmes
    -2.47
    Hol
    -2.46
    Surv
    -2.45
     Inquisitor
    -2.41
     Tac
    -2.39
    POSITIVE LOGITS
     electrons
    4.22
     electron
    3.68
     ions
    2.94
     nm
    2.78
     atoms
    2.78
     mitochond
    2.74
     atom
    2.64
     NET
    2.59
    ilver
    2.55
    ={
    2.48
    Activations Density 0.009%

    No Known Activations