© 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. 5226
    Prev
    Next
    INDEX
    Explanations

    expressions of disbelief or strong emotion

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Head Attr Weights
    0:0.03
    1:0.06
    2:0.12
    3:0.08
    4:0.05
    5:0.06
    6:0.08
    7:0.15
    8:0.11
    9:0.06
    10:0.08
    11:0.08
    Negative Logits
    reflect
    -1.24
     representation
    -1.19
    oult
    -1.16
     ¶
    -1.06
    advertisement
    -1.06
    natureconservancy
    -1.04
     nond
    -1.02
    tein
    -1.01
     namely
    -0.98
     arbitration
    -0.97
    POSITIVE LOGITS
    ????????
    1.13
     Butterfly
    1.12
     pandemonium
    1.11
     Babe
    1.08
     Freak
    1.07
    ????
    1.07
     Clown
    1.07
     havoc
    1.05
     Polic
    1.01
    ?????
    1.00
    Activations Density 0.013%

    No Known Activations