© 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. 9705
    Prev
    Next
    INDEX
    Explanations

    references to updates, corrections, or revisions in articles

    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
    0:0.02
    1:0.02
    2:0.04
    3:0.06
    4:0.15
    5:0.31
    6:0.02
    7:0.03
    8:0.03
    9:0.20
    10:0.03
    11:0.03
    Negative Logits
     yourself
    -3.23
     anyways
    -3.02
    yet
    -3.01
     yourselves
    -2.90
     yet
    -2.76
     anymore
    -2.71
     anyway
    -2.70
     huh
    -2.64
     ripe
    -2.52
    oire
    -2.42
    POSITIVE LOGITS
    Correct
    3.27
     incorrectly
    2.95
    Clar
    2.86
    iscal
    2.79
     incorrect
    2.73
     centrif
    2.68
     errone
    2.65
     Correct
    2.62
     mistakenly
    2.58
     Correction
    2.50
    Activations Density 0.021%

    No Known Activations