© 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. 13173
    Prev
    Next
    INDEX
    Explanations

    references to titles and power dynamics within a hierarchical structure

    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
    0:0.18
    1:0.07
    2:0.08
    3:0.07
    4:0.05
    5:0.04
    6:0.10
    7:0.08
    8:0.03
    9:0.04
    10:0.14
    11:0.05
    Negative Logits
    MK
    -3.62
     MK
    -3.59
     Mushroom
    -3.56
     Spielberg
    -3.30
     Heidi
    -3.29
     Netanyahu
    -3.23
     IDF
    -3.22
     indu
    -3.08
     IU
    -3.04
     interf
    -3.00
    POSITIVE LOGITS
     Vale
    9.44
     Yang
    4.66
    Yang
    4.46
     Atlas
    4.21
     Beacon
    4.10
    Blake
    4.07
     Jaune
    3.97
     Blake
    3.90
     Torch
    3.87
     Vox
    3.84
    Activations Density 0.000%

    No Known Activations