© 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. 10-ATT-KK
    11. 15274
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and governmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.02
    2:0.04
    3:0.04
    4:0.04
    5:0.11
    6:0.02
    7:0.04
    8:0.02
    9:0.51
    10:0.02
    11:0.06
    Negative Logits
    who
    -2.43
    rates
    -2.31
     compares
    -2.24
     Flavoring
    -2.18
    utics
    -2.17
    iates
    -2.12
    ames
    -2.08
     harms
    -2.02
    izes
    -1.99
    deals
    -1.99
    POSITIVE LOGITS
     paused
    3.16
     reinstated
    3.15
     disappearing
    3.14
     terminated
    3.09
     canceled
    3.03
    pleted
    3.02
     gone
    3.02
     completed
    3.01
     locked
    2.98
     silenced
    2.98
    Activations Density 0.426%

    No Known Activations