© 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 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. 11742
    Prev
    Next
    INDEX
    Explanations

    contact information or calls to action within text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    expressions and concepts related to identity and social roles

    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
    0:0.10
    1:0.06
    2:0.14
    3:0.12
    4:0.03
    5:0.04
    6:0.10
    7:0.07
    8:0.08
    9:0.05
    10:0.08
    11:0.07
    Negative Logits
     undet
    -1.03
    Reloaded
    -1.03
     vulner
    -1.01
    geries
    -1.00
     ignition
    -0.96
     grammar
    -0.96
     batch
    -0.95
     Healer
    -0.95
     Avalon
    -0.94
     Forge
    -0.92
    POSITIVE LOGITS
     istg
    1.22
     Marketable
    1.21
     msec
    1.18
     Supplementary
    1.15
    Likewise
    1.14
     Ratings
    1.13
     accordingly
    1.12
    Similarly
    1.08
     Likewise
    1.08
    NBC
    1.07
    Activations Density 0.050%

    No Known Activations