© 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. 5-ATT-KK
    11. 24720
    Prev
    Next
    INDEX
    Explanations

    mentions of significant actions or events relating to organizations or individuals

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.01
    1:0.03
    2:0.06
    3:0.11
    4:0.03
    5:0.07
    6:0.02
    7:0.03
    8:0.38
    9:0.09
    10:0.08
    11:0.06
    Negative Logits
     [|
    -1.62
    !:
    -1.60
     (~
    -1.54
    illac
    -1.53
     Reincarn
    -1.52
    yan
    -1.51
     Edit
    -1.51
    uscript
    -1.49
    GBT
    -1.42
    [_
    -1.35
    POSITIVE LOGITS
    ADVERTISEMENT
    1.64
    arent
    1.56
    Products
    1.56
    aceae
    1.48
    ALTH
    1.40
    ESA
    1.39
    igation
    1.37
    ILA
    1.36
     affairs
    1.35
    Maria
    1.34
    Activations Density 0.036%

    No Known Activations