© 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. 16837
    Prev
    Next
    INDEX
    Explanations

    references to frequency and patterns of events or behaviors

    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
    0:0.08
    1:0.18
    2:0.06
    3:0.05
    4:0.02
    5:0.01
    6:0.23
    7:0.08
    8:0.01
    9:0.03
    10:0.11
    11:0.08
    Negative Logits
    fecture
    -3.06
    istration
    -2.81
    OTA
    -2.65
    fect
    -2.64
     ACE
    -2.51
     Ake
    -2.47
     propos
    -2.41
    arse
    -2.40
     DIRECT
    -2.37
    poral
    -2.36
    POSITIVE LOGITS
     Wall
    8.82
    Wall
    8.16
     wall
    6.34
     Walls
    6.10
    wall
    5.95
     walls
    4.87
     WS
    3.79
     Wallace
    3.79
     wallpaper
    3.75
     hedge
    3.57
    Activations Density 0.044%

    No Known Activations