© 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. 7877
    Prev
    Next
    INDEX
    Explanations

    references to critique or controversy in discussions

    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
    0:0.19
    1:0.05
    2:0.10
    3:0.05
    4:0.05
    5:0.03
    6:0.05
    7:0.21
    8:0.03
    9:0.05
    10:0.10
    11:0.05
    Negative Logits
     Colonial
    -3.00
     Galaxy
    -2.75
    Wing
    -2.73
     Daytona
    -2.62
     Richmond
    -2.57
     Galactic
    -2.50
     Carlton
    -2.43
     Hampton
    -2.42
     Baptist
    -2.40
     Bom
    -2.39
    POSITIVE LOGITS
     �
    6.11
    �
    5.11
    ł
    4.38
    š
    4.18
    �
    4.08
    ć
    3.80
    č
    3.73
     �
    3.47
    �
    3.46
     Sloven
    3.39
    Activations Density 0.009%

    No Known Activations