© 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. 17245
    Prev
    Next
    INDEX
    Explanations

    linguistic constructs that express opinion or commentary

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.03
    3:0.04
    4:0.14
    5:0.13
    6:0.02
    7:0.04
    8:0.02
    9:0.41
    10:0.02
    11:0.05
    Negative Logits
     utilization
    -2.32
     authorization
    -2.26
    rus
    -2.16
     Authorization
    -2.12
     estimate
    -2.09
     allocation
    -2.08
     excessive
    -2.03
    igation
    -2.02
     concentration
    -1.94
     using
    -1.93
    POSITIVE LOGITS
    warts
    3.17
     haun
    3.11
     motiv
    3.02
     inspires
    3.01
     shines
    2.99
     separates
    2.65
     emerges
    2.58
     mattered
    2.54
    makes
    2.53
     distinguishes
    2.49
    Activations Density 0.194%

    No Known Activations