© 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. 5212
    Prev
    Next
    INDEX
    Explanations

    references to location, events, or specific entities

    oai_token-act-pair · gpt-3.5-turbo
    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
    1:0.04
    2:0.13
    3:0.20
    4:0.02
    5:0.02
    6:0.08
    7:0.15
    8:0.06
    9:0.06
    10:0.07
    11:0.09
    Negative Logits
     depressive
    -1.15
     peak
    -1.10
     salsa
    -1.03
     tsun
    -1.03
     peaks
    -1.03
    ashtra
    -1.00
    ć
    -0.99
    peak
    -0.98
    hedon
    -0.97
    �
    -0.96
    POSITIVE LOGITS
    zanne
    1.26
     GOODMAN
    1.22
    ophon
    1.14
     pse
    1.14
     Dare
    1.13
     Helm
    1.13
    ernel
    1.12
    ocument
    1.11
    DragonMagazine
    1.09
    arthed
    1.09
    Activations Density 0.010%

    No Known Activations