© 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. 23258
    Prev
    Next
    INDEX
    Explanations

    phrases or transitions that indicate a timeline or sequence of events

    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
    0:0.07
    1:0.10
    2:0.07
    3:0.10
    4:0.08
    5:0.04
    6:0.11
    7:0.10
    8:0.04
    9:0.08
    10:0.06
    11:0.10
    Negative Logits
     Legislative
    -2.93
     administrative
    -2.75
     legislators
    -2.74
     legislative
    -2.72
     Constitutional
    -2.66
     constitutional
    -2.62
     Commissioners
    -2.57
     auxiliary
    -2.55
     expansions
    -2.55
     Administrative
    -2.46
    POSITIVE LOGITS
    ouf
    3.22
    20439
    3.16
    ��
    3.13
    ★★
    3.00
    deen
    2.94
    76561
    2.87
     RAF
    2.77
    isine
    2.72
    tumblr
    2.70
    netflix
    2.66
    Activations Density 0.001%

    No Known Activations