© 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. 9-ATT-KK
    11. 19887
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or limitations involving production or processing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.04
    2:0.08
    3:0.05
    4:0.04
    5:0.03
    6:0.18
    7:0.04
    8:0.03
    9:0.27
    10:0.04
    11:0.04
    Negative Logits
     Lur
    -4.00
    oths
    -3.46
    Wi
    -3.35
     Brow
    -3.30
     UL
    -3.23
     ELE
    -3.19
     Ic
    -3.18
     Hopkins
    -3.17
     Nid
    -3.09
     Huck
    -3.08
    POSITIVE LOGITS
    produ
    6.05
     Produ
    5.88
     produce
    5.70
     Production
    5.65
     produced
    5.61
    Produ
    5.53
     producing
    5.50
    production
    5.36
    Production
    5.26
    produced
    5.25
    Activations Density 0.007%

    No Known Activations