© 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. 9-ATT-KK
    11. 5671
    Prev
    Next
    INDEX
    Explanations

    words related to messages and communication

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.11
    1:0.05
    2:0.04
    3:0.16
    4:0.07
    5:0.16
    6:0.05
    7:0.06
    8:0.10
    9:0.02
    10:0.09
    11:0.04
    Negative Logits
     roundup
    -2.07
    )</
    -1.92
     disapp
    -1.78
     SPORTS
    -1.76
    Reviewer
    -1.75
     ‎
    -1.70
     Survey
    -1.68
    hens
    -1.66
     Picks
    -1.64
     proced
    -1.63
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    2.12
    ilde
    1.95
    aina
    1.88
    ENSE
    1.86
    Gray
    1.79
    aque
    1.75
    role
    1.74
    uty
    1.73
    enez
    1.72
    anooga
    1.71
    Activations Density 0.001%

    No Known Activations