© 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. 14288
    Prev
    Next
    INDEX
    Explanations

    unnumbered lists within a document

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

    terms related to business relationships and transactions, particularly in the context of suppliers, manufacturers, and the insurance industry

    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
    0:0.02
    1:0.03
    2:0.06
    3:0.05
    4:0.03
    5:0.06
    6:0.16
    7:0.34
    8:0.05
    9:0.03
    10:0.08
    11:0.06
    Negative Logits
     prol
    -1.25
    poral
    -1.14
    Coach
    -1.10
     Corps
    -1.09
     jog
    -1.09
     Insp
    -1.08
    Narr
    -1.08
     Sorceress
    -1.06
     narrated
    -1.05
    POL
    -1.04
    POSITIVE LOGITS
    bid
    1.36
     beware
    1.30
     sued
    1.20
    abel
    1.15
     contacted
    1.12
    consumer
    1.12
     subcontract
    1.09
     blacklist
    1.06
     warranties
    1.04
    hips
    1.02
    Activations Density 0.171%

    No Known Activations