© 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. 3-ATT-KK
    11. 10658
    Prev
    Next
    INDEX
    Explanations

    abstract and vague references to concepts, often questioning clarity or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.04
    2:0.16
    3:0.07
    4:0.02
    5:0.04
    6:0.05
    7:0.16
    8:0.25
    9:0.03
    10:0.07
    11:0.04
    Negative Logits
     Kul
    -0.95
     Krug
    -0.92
     Das
    -0.92
    etheus
    -0.90
     Zer
    -0.90
     Ur
    -0.84
    uzzle
    -0.82
     Jag
    -0.81
    eeds
    -0.80
     Erie
    -0.80
    POSITIVE LOGITS
    ONSORED
    1.14
    VERTISEMENT
    0.92
     meets
    0.92
    Applic
    0.91
     disapp
    0.87
    disabled
    0.87
     <-
    0.87
    Parser
    0.85
    Exception
    0.85
    PLIED
    0.84
    Activations Density 0.187%

    No Known Activations