© 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. 20201
    Prev
    Next
    INDEX
    Explanations

    phrases that involve pairing or listing items or actions

    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
    0:0.09
    1:0.03
    2:0.04
    3:0.06
    4:0.19
    5:0.04
    6:0.03
    7:0.25
    8:0.03
    9:0.06
    10:0.04
    11:0.07
    Negative Logits
     food
    -4.45
    Food
    -4.14
     meal
    -4.09
    food
    -3.98
     foods
    -3.95
     eating
    -3.88
     meals
    -3.80
     eaten
    -3.76
     Eating
    -3.63
    meat
    -3.57
    POSITIVE LOGITS
    ymm
    2.91
     Remastered
    2.83
     Freem
    2.83
     Merrill
    2.57
    uliffe
    2.57
    ROM
    2.53
     Boyle
    2.49
    STEM
    2.47
     McAuliffe
    2.46
    agall
    2.44
    Activations Density 0.005%

    No Known Activations