© 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. 7713
    Prev
    Next
    INDEX
    Explanations

    metrics and statistics related to voting behavior and support

    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
    0:0.03
    1:0.02
    2:0.02
    3:0.06
    4:0.06
    5:0.16
    6:0.09
    7:0.06
    8:0.01
    9:0.34
    10:0.03
    11:0.07
    Negative Logits
    ometimes
    -2.79
    hov
    -2.71
    ��
    -2.63
    Haunted
    -2.50
    inventoryQuantity
    -2.45
    acly
    -2.35
    thora
    -2.19
    iddled
    -2.14
    obyl
    -2.13
    inker
    -2.11
    POSITIVE LOGITS
     votes
    3.97
     abst
    3.95
     opposed
    3.82
     voting
    3.81
     voted
    3.77
     veto
    3.63
     signatures
    3.62
     agreeing
    3.54
     opposing
    3.50
    legates
    3.47
    Activations Density 0.167%

    No Known Activations