© 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. 14191
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to news articles or reports

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    prominent keywords and phrases that suggest importance or emphasis in a news context

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.11
    2:0.10
    3:0.05
    4:0.04
    5:0.05
    6:0.14
    7:0.10
    8:0.11
    9:0.05
    10:0.07
    11:0.09
    Negative Logits
    ignty
    -0.89
     Prophet
    -0.84
    Finish
    -0.79
     thereof
    -0.78
    venge
    -0.78
    #$
    -0.77
     Sabbath
    -0.77
    『
    -0.76
     [|
    -0.74
    iphate
    -0.74
    POSITIVE LOGITS
    osponsors
    0.98
     GOODMAN
    0.87
    oking
    0.86
    kinson
    0.85
    advertisement
    0.81
    gart
    0.80
    nick
    0.80
    abling
    0.79
    enegger
    0.78
    mining
    0.78
    Activations Density 0.786%

    No Known Activations