© 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. 13349
    Prev
    Next
    INDEX
    Explanations

    references to statistical data or findings

    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
    0:0.13
    1:0.03
    2:0.15
    3:0.04
    4:0.04
    5:0.11
    6:0.09
    7:0.11
    8:0.05
    9:0.12
    10:0.03
    11:0.03
    Negative Logits
     torpedo
    -3.00
     Rhodes
    -2.92
     pigeon
    -2.44
    ANE
    -2.42
     Raymond
    -2.34
     CAS
    -2.28
     ASA
    -2.15
     flies
    -2.14
     Marino
    -2.13
    nance
    -2.13
    POSITIVE LOGITS
     �
    5.81
    �
    4.94
    �
    3.30
    Elsa
    3.30
    �
    3.25
    �
    3.17
     Blizz
    3.10
    َ
    3.05
     Elsa
    3.04
    מ
    3.01
    Activations Density 0.246%

    No Known Activations