© 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. 11942
    Prev
    Next
    INDEX
    Explanations

    references to updates and notifications in various contexts

    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
    0:0.03
    1:0.02
    2:0.04
    3:0.07
    4:0.11
    5:0.46
    6:0.03
    7:0.03
    8:0.02
    9:0.09
    10:0.02
    11:0.04
    Negative Logits
    )).
    -3.20
    ADVERTISEMENT
    -2.94
    would
    -2.89
     whenever
    -2.86
    often
    -2.67
     preferable
    -2.66
    )),
    -2.62
     preferably
    -2.61
     ideal
    -2.60
     wherever
    -2.60
    POSITIVE LOGITS
     now
    4.16
     NOW
    3.59
     confirms
    3.55
     continues
    3.34
     Yesterday
    3.29
    now
    3.27
    !]
    3.26
     Previously
    3.24
     HAS
    3.19
     Emails
    3.17
    Activations Density 0.096%

    No Known Activations