© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 26259
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "was" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.02
    2:0.06
    3:0.10
    4:0.06
    5:0.10
    6:0.08
    7:0.02
    8:0.05
    9:0.12
    10:0.13
    11:0.16
    Negative Logits
     amen
    -1.52
     [|
    -1.33
    "},"
    -1.28
     [&
    -1.16
     Franchise
    -1.12
     Handbook
    -1.12
    .�
    -1.12
    soever
    -1.11
     Creator
    -1.08
     experien
    -1.07
    POSITIVE LOGITS
    aughs
    1.29
    trap
    1.22
     smelled
    1.21
     collided
    1.12
    agne
    1.11
    quick
    1.08
    ousy
    1.08
    tch
    1.07
     laced
    1.05
    furt
    1.03
    Activations Density 0.078%

    No Known Activations