© 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. 24962
    Prev
    Next
    INDEX
    Explanations

    symbols or punctuation marks that indicate emphasis or importance

    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
    0:0.04
    1:0.04
    2:0.05
    3:0.07
    4:0.04
    5:0.13
    6:0.07
    7:0.04
    8:0.06
    9:0.08
    10:0.20
    11:0.14
    Negative Logits
    named
    -1.66
    align
    -1.63
    esty
    -1.62
    taboola
    -1.59
    oat
    -1.59
    notation
    -1.57
    Position
    -1.50
     Reported
    -1.48
    TOP
    -1.44
    Tweet
    -1.42
    POSITIVE LOGITS
     willpower
    1.67
     relapse
    1.64
     despair
    1.63
     subconscious
    1.62
     psychosis
    1.57
    ocrin
    1.56
    "}],"
    1.51
     mastering
    1.50
     Mothers
    1.46
     capitalist
    1.44
    Activations Density 0.000%

    No Known Activations