© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 14531
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking control or asserting dominance

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    conditional statements and requirements for success or action

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.02
    1:0.05
    2:0.04
    3:0.02
    4:0.03
    5:0.20
    6:0.04
    7:0.04
    8:0.05
    9:0.27
    10:0.06
    11:0.13
    Negative Logits
    azon
    -1.49
     Jaw
    -1.46
    ansk
    -1.39
     wom
    -1.34
     retweet
    -1.34
     Rasmussen
    -1.33
     Moments
    -1.30
    arah
    -1.29
     flanked
    -1.27
     Fowler
    -1.26
    POSITIVE LOGITS
     certific
    1.71
    plementation
    1.55
     please
    1.50
     PLEASE
    1.47
     properly
    1.45
     therape
    1.45
     optimum
    1.42
    elsius
    1.42
    agame
    1.42
    transfer
    1.40
    Activations Density 0.016%

    No Known Activations