© 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. 38407
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.03
    2:0.05
    3:0.06
    4:0.05
    5:0.05
    6:0.37
    7:0.06
    8:0.06
    9:0.08
    10:0.07
    11:0.05
    Negative Logits
     mustache
    -1.25
     facade
    -1.20
    hement
    -1.18
     masturbation
    -1.15
     diarrhea
    -1.15
    pection
    -1.14
     hindsight
    -1.13
    FTWARE
    -1.12
     anonymity
    -1.11
    ateurs
    -1.10
    POSITIVE LOGITS
    EStream
    1.66
    zon
    1.54
    bash
    1.44
    obin
    1.38
    代
    1.36
    acher
    1.32
    intel
    1.29
    roth
    1.29
    schild
    1.28
    ree
    1.25
    Activations Density 0.005%

    No Known Activations