© 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. 12800
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a subjective opinion or commentary on various subjects

    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
    1:0.07
    2:0.17
    3:0.05
    4:0.04
    5:0.02
    6:0.08
    7:0.13
    8:0.03
    9:0.04
    10:0.11
    11:0.02
    Negative Logits
    enegger
    -2.75
     bamboo
    -2.71
     Frie
    -2.64
     Greenwood
    -2.59
     franc
    -2.57
     Roche
    -2.51
     Tunis
    -2.46
    Browser
    -2.45
    Ireland
    -2.44
    atto
    -2.44
    POSITIVE LOGITS
     Alex
    7.73
    Alex
    6.44
     Alexandra
    4.61
     ALE
    4.43
     Alexis
    4.18
     Alexand
    3.94
     Ale
    3.46
     Alexander
    3.38
     Aly
    3.38
     Ivan
    3.35
    Activations Density 0.017%

    No Known Activations