© 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. 20855
    Prev
    Next
    INDEX
    Explanations

    products and terms related to cleaning, particularly for keyboards and hygiene

    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
    0:0.38
    1:0.01
    2:0.13
    3:0.08
    4:0.02
    5:0.08
    6:0.04
    7:0.04
    8:0.08
    9:0.05
    10:0.02
    11:0.02
    Negative Logits
     Films
    -3.44
     documentaries
    -3.32
    Netflix
    -2.97
     filmmaking
    -2.96
    hyde
    -2.95
     defund
    -2.94
    flix
    -2.91
    FactoryReloaded
    -2.90
     viewership
    -2.89
     filming
    -2.88
    POSITIVE LOGITS
     keyboards
    5.79
     keyboard
    5.16
     typew
    4.84
     typing
    4.81
     Keyboard
    4.67
     Typ
    4.44
     typed
    3.91
     switches
    3.90
     keys
    3.87
     Cherry
    3.76
    Activations Density 0.044%

    No Known Activations