© 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. 10531
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names related to significant individuals and concepts

    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
    0:0.03
    1:0.02
    2:0.02
    3:0.02
    4:0.05
    5:0.47
    6:0.02
    7:0.03
    8:0.02
    9:0.17
    10:0.02
    11:0.06
    Negative Logits
     than
    -3.96
     Than
    -3.61
    than
    -3.60
    internet
    -2.60
     INFO
    -2.45
    Updated
    -2.42
     arrang
    -2.39
    >(
    -2.36
    asm
    -2.34
    RESULTS
    -2.33
    POSITIVE LOGITS
     before
    3.98
     foregoing
    3.46
     beforehand
    3.38
     earlier
    3.22
     prior
    3.13
    before
    3.08
     preceding
    3.04
     previously
    2.94
     others
    2.77
     previous
    2.56
    Activations Density 0.103%

    No Known Activations