© 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. 5437
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of storage in energy-related topics

    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
    0:0.05
    1:0.08
    2:0.07
    3:0.06
    4:0.08
    5:0.12
    6:0.07
    7:0.08
    8:0.08
    9:0.07
    10:0.09
    11:0.08
    Negative Logits
    theless
    -1.64
     meanwhile
    -1.47
     Aires
    -1.43
    ‎
    -1.39
    etheless
    -1.39
    Footnote
    -1.35
    forth
    -1.30
    HAM
    -1.28
    surprisingly
    -1.24
    asca
    -1.23
    POSITIVE LOGITS
    tc
    1.45
    Interstitial
    1.34
    layout
    1.31
    oto
    1.28
     url
    1.25
    tx
    1.23
    Load
    1.18
    ixel
    1.18
    vertis
    1.18
     URL
    1.17
    Activations Density 0.003%

    No Known Activations