© 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. 5380
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal or judicial concepts

    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
    1:0.11
    2:0.11
    3:0.02
    4:0.07
    5:0.09
    6:0.11
    7:0.10
    8:0.07
    9:0.06
    10:0.11
    11:0.05
    Negative Logits
    Roaming
    -1.40
    artney
    -1.38
    OPA
    -1.27
    orious
    -1.27
    perty
    -1.24
    FUL
    -1.23
    illary
    -1.20
    terday
    -1.17
    obbies
    -1.15
     FANTASY
    -1.15
    POSITIVE LOGITS
    ⓘ
    1.43
    ビ
    1.38
     peril
    1.16
    ディ
    1.14
    etc
    1.13
     redistributed
    1.11
     裏�
    1.08
    thia
    1.07
     etc
    1.06
    forcement
    1.04
    Activations Density 1.204%

    No Known Activations