© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 17418
    Prev
    Next
    INDEX
    Explanations

    references to visual content such as images and videos

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.22
    1:0.08
    2:0.09
    3:0.07
    4:0.05
    5:0.03
    6:0.10
    7:0.10
    8:0.05
    9:0.04
    10:0.07
    11:0.06
    Negative Logits
    Ford
    -4.01
     Allaah
    -3.75
     Ford
    -3.55
     Donn
    -3.31
    Indiana
    -3.23
     stub
    -3.18
     Ulster
    -3.13
     Rider
    -3.08
    nih
    -3.03
     tire
    -3.01
    POSITIVE LOGITS
     Alexis
    7.06
     Alexand
    5.00
    Alex
    4.25
     Alexandria
    3.44
     Alexandra
    3.30
    ��
    3.22
     Alex
    3.20
     Ars
    3.09
     Mate
    3.07
     Cascade
    3.06
    Activations Density 0.001%

    No Known Activations