© 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. 2552
    Prev
    Next
    INDEX
    Explanations

    phrases related to gun control discussions

    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
    1:0.03
    2:0.10
    3:0.04
    4:0.06
    5:0.04
    6:0.18
    7:0.04
    8:0.09
    9:0.20
    10:0.02
    11:0.04
    Negative Logits
     phyl
    -5.14
    abase
    -3.92
     cemetery
    -3.48
    agall
    -3.45
     polymorph
    -3.40
    abases
    -3.35
    anguage
    -3.29
    ravel
    -3.22
     castle
    -3.21
     graveyard
    -3.17
    POSITIVE LOGITS
     Watt
    10.35
     Watts
    8.76
     watt
    6.58
     watts
    6.23
    atts
    5.14
    Tenn
    4.89
     MW
    4.66
     Thunderbolt
    4.40
     Waters
    4.35
     Charg
    4.18
    Activations Density 0.003%

    No Known Activations