© 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. 24900
    Prev
    Next
    INDEX
    Explanations

    references to adaptations of various literary works

    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
    0:0.02
    1:0.00
    2:0.04
    3:0.05
    4:0.16
    5:0.02
    6:0.02
    7:0.36
    8:0.03
    9:0.03
    10:0.12
    11:0.10
    Negative Logits
    inguished
    -1.64
    hesion
    -1.61
    ailability
    -1.61
    rimination
    -1.58
    pora
    -1.52
     distingu
    -1.44
    bery
    -1.43
    antry
    -1.43
    ablishment
    -1.43
    atography
    -1.42
    POSITIVE LOGITS
     satirical
    1.52
     Patriarch
    1.33
     Ott
    1.27
     Original
    1.24
     orally
    1.23
     Divinity
    1.19
     Ald
    1.18
     tru
    1.18
     extracts
    1.17
     shortened
    1.17
    Activations Density 0.003%

    No Known Activations