© 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. 17422
    Prev
    Next
    INDEX
    Explanations

    phrases related to public opinion and approval ratings

    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
    0:0.04
    1:0.14
    2:0.07
    3:0.06
    4:0.10
    5:0.04
    6:0.10
    7:0.14
    8:0.03
    9:0.05
    10:0.05
    11:0.12
    Negative Logits
    ombat
    -2.70
    ovember
    -2.68
    cision
    -2.60
    ospace
    -2.60
     Exception
    -2.40
     Explos
    -2.29
    Event
    -2.22
     Printing
    -2.19
    Exception
    -2.18
     CODE
    -2.18
    POSITIVE LOGITS
     unfavorable
    4.95
     favorable
    4.87
     favorably
    4.07
    avorable
    3.79
     favourable
    3.62
     unf
    3.38
     negatives
    3.28
     neutral
    3.17
     flattering
    3.14
     negative
    3.13
    Activations Density 0.002%

    No Known Activations