© 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. 10372
    Prev
    Next
    INDEX
    Explanations

    references to modular design and componentization in programming

    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
    0:0.05
    1:0.03
    2:0.10
    3:0.12
    4:0.09
    5:0.05
    6:0.12
    7:0.05
    8:0.06
    9:0.07
    10:0.09
    11:0.12
    Negative Logits
    itatively
    -1.48
    izons
    -1.46
    itudes
    -1.45
    quist
    -1.44
     Morty
    -1.32
    ationally
    -1.30
    onsense
    -1.28
    mson
    -1.27
    guyen
    -1.27
    hesda
    -1.27
    POSITIVE LOGITS
    urb
    1.50
     Dating
    1.39
     Seller
    1.19
    idy
    1.14
    closed
    1.14
    anned
    1.14
    ruption
    1.14
    ability
    1.13
    ophon
    1.12
    runner
    1.10
    Activations Density 0.002%

    No Known Activations