© 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. 10-ATT-KK
    11. 19861
    Prev
    Next
    INDEX
    Explanations

    recurring phrases related to article continuations or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.04
    3:0.24
    4:0.21
    5:0.06
    6:0.04
    7:0.04
    8:0.13
    9:0.05
    10:0.03
    11:0.04
    Negative Logits
    edom
    -2.95
     Bane
    -2.38
    ,[
    -2.38
    ,,,,,,,,
    -2.13
     explo
    -2.08
    ======
    -2.03
     nineteen
    -2.03
    resy
    -2.02
    ighed
    -2.00
     fucking
    -1.99
    POSITIVE LOGITS
    Story
    2.99
     RCMP
    2.68
    continue
    2.64
     CFL
    2.60
     aboriginal
    2.54
     Manitoba
    2.43
     continues
    2.39
    english
    2.37
     Canadians
    2.34
     Continue
    2.31
    Activations Density 0.004%

    No Known Activations