© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 12215
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts in opinions or experiences

    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
    0:0.09
    1:0.08
    2:0.07
    3:0.03
    4:0.04
    5:0.02
    6:0.32
    7:0.11
    8:0.04
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
    erion
    -2.79
    redits
    -2.54
     guiActiveUn
    -2.52
     Reg
    -2.48
     revenues
    -2.45
     Tub
    -2.38
    Cour
    -2.38
     reconciliation
    -2.37
    mable
    -2.37
     Test
    -2.37
    POSITIVE LOGITS
     pick
    7.66
    Pick
    7.16
     Pick
    7.15
    pick
    6.98
     picks
    6.55
     picking
    5.78
     Picks
    5.72
    picking
    5.46
     picked
    5.36
     selections
    4.04
    Activations Density 0.068%

    No Known Activations