© 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. 3-ATT-KK
    11. 5959
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate processes or actions related to improvement and transformation

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.03
    2:0.18
    3:0.03
    4:0.03
    5:0.04
    6:0.09
    7:0.05
    8:0.17
    9:0.12
    10:0.10
    11:0.07
    Negative Logits
    ukemia
    -1.26
     Semin
    -1.18
     Wat
    -1.17
     Bounty
    -1.15
    Hung
    -1.13
    Lens
    -1.10
     Fell
    -1.08
     Illum
    -1.07
     fest
    -1.07
    Flor
    -1.05
    POSITIVE LOGITS
     safely
    2.08
     cheaply
    1.79
     efficiently
    1.74
     easily
    1.67
     securely
    1.58
     anytime
    1.56
    rehend
    1.50
    ibly
    1.46
     seamlessly
    1.45
    ivably
    1.43
    Activations Density 0.061%

    No Known Activations