© 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. 22661
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and contextually important action descriptions

    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
    0:0.15
    1:0.12
    2:0.05
    3:0.04
    4:0.03
    5:0.03
    6:0.11
    7:0.05
    8:0.02
    9:0.04
    10:0.25
    11:0.05
    Negative Logits
    amation
    -3.13
     Giuliani
    -3.01
     Pacers
    -2.98
    atum
    -2.95
    immune
    -2.87
     Gent
    -2.85
    Palestinian
    -2.84
     Huang
    -2.83
     Hayward
    -2.78
     immutable
    -2.77
    POSITIVE LOGITS
     Cra
    9.70
    Cra
    9.02
     cra
    4.96
     Dra
    4.93
     Pra
    4.19
     Cree
    4.17
     CRA
    4.04
     dra
    3.95
    cr
    3.92
     Crate
    3.91
    Activations Density 0.001%

    No Known Activations