© 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. 17463
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or efforts made in support of a cause or person

    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
    0:0.16
    1:0.07
    2:0.04
    3:0.05
    4:0.10
    5:0.02
    6:0.14
    7:0.13
    8:0.02
    9:0.05
    10:0.07
    11:0.08
    Negative Logits
     Rath
    -2.98
    agos
    -2.93
    bnb
    -2.92
    APTER
    -2.71
    ░░
    -2.53
    Border
    -2.49
    Uber
    -2.48
    Leaks
    -2.48
    entin
    -2.47
    ickr
    -2.42
    POSITIVE LOGITS
     cheer
    5.88
     cheering
    5.25
     volleyball
    4.06
     cheered
    3.96
     athletics
    3.87
     cheers
    3.87
     gymn
    3.80
     rugby
    3.71
     soccer
    3.71
     athlet
    3.56
    Activations Density 0.001%

    No Known Activations