© 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. 21651
    Prev
    Next
    INDEX
    Explanations

    questions or phrases expressing uncertainty or needing clarification

    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
    1:0.10
    2:0.07
    3:0.06
    4:0.09
    5:0.02
    6:0.10
    7:0.12
    8:0.02
    9:0.03
    10:0.10
    11:0.07
    Negative Logits
     Saints
    -3.08
     mast
    -2.97
     Lions
    -2.78
     Bowman
    -2.76
    acca
    -2.65
     Saud
    -2.60
     Lion
    -2.56
    obil
    -2.53
    addin
    -2.42
    aints
    -2.41
    POSITIVE LOGITS
     entropy
    7.68
    ropy
    4.35
     horm
    3.73
     atoms
    3.20
    ministic
    3.15
     Eucl
    3.08
     isot
    3.05
     electron
    3.01
     random
    2.97
     universes
    2.96
    Activations Density 0.000%

    No Known Activations