© 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. 10-ATT-KK
    11. 17105
    Prev
    Next
    INDEX
    Explanations

    quotes and phrases related to third parties or external entities

    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
    0:0.07
    1:0.21
    2:0.07
    3:0.06
    4:0.05
    5:0.03
    6:0.10
    7:0.11
    8:0.05
    9:0.05
    10:0.05
    11:0.10
    Negative Logits
    quit
    -2.53
     Lear
    -2.46
    era
    -2.45
     Symbol
    -2.35
     Mour
    -2.35
    quick
    -2.30
    �
    -2.21
     Regiment
    -2.20
     ›
    -2.17
     Temper
    -2.14
    POSITIVE LOGITS
    third
    4.52
     third
    4.32
    Third
    4.32
     Third
    4.09
    Fourth
    3.50
     intermedi
    3.12
     Fourth
    2.84
     Marketplace
    2.84
    fourth
    2.83
     vendors
    2.67
    Activations Density 0.005%

    No Known Activations