© 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. 2-ATT-KK
    11. 23006
    Prev
    Next
    INDEX
    Explanations

    people's names and positions in various political, legal, and sports contexts

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

    references to former government officials and their roles or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.03
    2:0.05
    3:0.20
    4:0.03
    5:0.07
    6:0.05
    7:0.07
    8:0.12
    9:0.05
    10:0.12
    11:0.06
    Negative Logits
    ramid
    -1.17
     unfocusedRange
    -1.15
     RIGHT
    -1.11
     dots
    -1.09
     nostalg
    -1.08
     Interstellar
    -1.07
     Zup
    -1.07
    _-
    -1.04
     anecd
    -1.03
    _-_
    -1.02
    POSITIVE LOGITS
    pired
    1.29
     operative
    1.17
    smoking
    1.14
    ghazi
    1.07
     Olympia
    1.05
     accuser
    1.04
    workers
    1.04
     alike
    1.02
    20439
    1.02
     staffer
    1.01
    Activations Density 0.078%

    No Known Activations