© 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. 9-ATT-KK
    11. 5650
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue and responses in text

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.04
    1:0.04
    2:0.04
    3:0.09
    4:0.06
    5:0.05
    6:0.03
    7:0.05
    8:0.03
    9:0.02
    10:0.03
    11:0.46
    Negative Logits
    ,'
    -8.28
    .'
    -8.23
    ?'
    -7.98
    !'
    -7.57
    )'
    -7.13
    ','
    -6.62
    ]'
    -6.23
    ';
    -6.13
    ':
    -6.08
    ').
    -5.96
    POSITIVE LOGITS
     "
    8.36
     "...
    7.45
     "[
    7.38
     ".
    7.00
     "…
    6.85
     "(
    6.81
     "-
    6.55
     "#
    6.18
     "_
    6.08
     "@
    5.99
    Activations Density 0.413%

    No Known Activations