© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 8490
    Prev
    Next
    INDEX
    Explanations

    quantifiable data and references to specific entities

    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
    0:0.16
    1:0.16
    2:0.06
    3:0.05
    4:0.03
    5:0.02
    6:0.09
    7:0.08
    8:0.02
    9:0.04
    10:0.18
    11:0.05
    Negative Logits
     LIA
    -3.04
    ++++
    -3.01
    Lewis
    -2.90
    enegger
    -2.90
     EVE
    -2.85
     Gill
    -2.70
    utherland
    -2.67
    AAAAAAAA
    -2.64
    illes
    -2.63
     Galile
    -2.56
    POSITIVE LOGITS
     Dub
    9.40
    Dub
    7.68
     dub
    6.94
     Dul
    3.96
     Dup
    3.95
     Dum
    3.81
     Zub
    3.77
    Dim
    3.74
     Drum
    3.42
     Flu
    3.32
    Activations Density 0.004%

    No Known Activations