© 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. 9-ATT-KK
    11. 17977
    Prev
    Next
    INDEX
    Explanations

    specific symbols or unusual characters that suggest formatting or encoding issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.04
    2:0.03
    3:0.09
    4:0.16
    5:0.06
    6:0.10
    7:0.08
    8:0.09
    9:0.05
    10:0.11
    11:0.09
    Negative Logits
     Gron
    -2.76
     Garcia
    -2.63
     McGr
    -2.60
     Juice
    -2.58
     Thiel
    -2.52
     DeV
    -2.48
     Gil
    -2.45
     Essence
    -2.38
     Sic
    -2.32
     Bren
    -2.31
    POSITIVE LOGITS
    �
    5.38
    �
    3.63
     �
    3.34
    ‎
    3.27
     ›
    3.08
    ️
    3.07
    ¶
    3.06
    ————
    2.91
    ■
    2.86
     ‎
    2.81
    Activations Density 0.132%

    No Known Activations