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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 11270
    Prev
    Next
    INDEX
    Explanations

    significant metrics and indicators related to various organizations and activities

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

    No Comments

    Head Attr Weights
    0:0.03
    1:0.04
    2:0.22
    3:0.02
    4:0.03
    5:0.04
    6:0.07
    7:0.05
    8:0.06
    9:0.10
    10:0.08
    11:0.20
    Negative Logits
    anu
    -1.24
    istine
    -1.22
    ippy
    -1.19
     perspective
    -1.17
    leigh
    -1.17
    aca
    -1.15
     Winn
    -1.12
    jit
    -1.12
     Odyssey
    -1.11
    ebin
    -1.10
    POSITIVE LOGITS
     finalists
    1.61
     poisons
    1.36
    arters
    1.35
    emies
    1.34
     replacements
    1.30
     species
    1.29
    gars
    1.22
     additions
    1.21
     meats
    1.21
     incorpor
    1.20
    Activations Density 0.016%

    No Known Activations