© 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. 14409
    Prev
    Next
    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    contact information for individuals, particularly email addresses and phone numbers

    oai_token-act-pair · gpt-4o-mini
    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
    0:0.06
    1:0.22
    2:0.08
    3:0.04
    4:0.02
    5:0.07
    6:0.09
    7:0.06
    8:0.10
    9:0.05
    10:0.07
    11:0.08
    Negative Logits
     evapor
    -1.72
    chwitz
    -1.66
    ?",
    -1.64
     mould
    -1.62
     migrants
    -1.60
     prey
    -1.59
    ?".
    -1.59
     Poles
    -1.58
     divers
    -1.53
     bulldo
    -1.53
    POSITIVE LOGITS
    @
    2.07
    Blog
    1.98
    Jen
    1.87
    ゴン
    1.80
     quotes
    1.73
    biz
    1.72
    podcast
    1.72
    Hart
    1.71
    gallery
    1.68
    forum
    1.68
    Activations Density 0.006%

    No Known Activations