© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 9133
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases and expressions seeking clarification or guidance

    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
    2:0.10
    3:0.05
    4:0.01
    5:0.03
    6:0.07
    7:0.06
    8:0.15
    9:0.14
    10:0.07
    11:0.20
    Negative Logits
     Didn
    -1.11
    court
    -1.11
     shares
    -1.09
     FINAL
    -1.06
     msec
    -1.06
     none
    -1.06
     condolences
    -1.05
     Doesn
    -1.04
     hadn
    -1.03
    �
    -1.02
    POSITIVE LOGITS
    emis
    1.68
     behave
    1.32
     interact
    1.31
     navigate
    1.31
    essage
    1.31
    iqueness
    1.28
     fragmented
    1.27
    idth
    1.24
     volunte
    1.24
    kef
    1.23
    Activations Density 0.030%

    No Known Activations