© 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. 21101
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions and movements

    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
    0:0.10
    1:0.07
    2:0.07
    3:0.06
    4:0.16
    5:0.06
    6:0.06
    7:0.07
    8:0.04
    9:0.11
    10:0.04
    11:0.10
    Negative Logits
     millionaires
    -2.74
     Soup
    -2.55
     subscriptions
    -2.45
     Homeless
    -2.44
     multicultural
    -2.43
    stories
    -2.42
     tainted
    -2.38
    grown
    -2.38
    landish
    -2.37
     Elections
    -2.34
    POSITIVE LOGITS
     braking
    4.75
     maneuver
    4.45
     torque
    4.41
     manoeuv
    4.23
     immobil
    3.96
     brake
    3.96
     lateral
    3.93
     diseng
    3.90
     directional
    3.84
     perpendicular
    3.78
    Activations Density 0.296%

    No Known Activations