© 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. 9075
    Prev
    Next
    INDEX
    Explanations

    references to U.S. constitutional amendments or related legal principles

    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
    0:0.04
    1:0.03
    2:0.08
    3:0.06
    4:0.15
    5:0.14
    6:0.07
    7:0.09
    8:0.07
    9:0.12
    10:0.04
    11:0.07
    Negative Logits
    hedral
    -2.60
    tsky
    -2.47
     dynamics
    -2.45
    avid
    -2.42
    xual
    -2.35
     helicop
    -2.34
    zbollah
    -2.31
    zsche
    -2.30
    talk
    -2.23
     psyche
    -2.21
    POSITIVE LOGITS
     shall
    3.69
    shall
    3.54
     hereby
    3.21
     hath
    2.98
     SHALL
    2.82
     thereof
    2.73
    }:
    2.52
    FORE
    2.47
     authorize
    2.47
    enture
    2.38
    Activations Density 0.019%

    No Known Activations