© 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. 6339
    Prev
    Next
    INDEX
    Explanations

    key terms related to publishing and literary reviews

    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
    0:0.11
    1:0.05
    2:0.08
    3:0.06
    4:0.04
    5:0.03
    6:0.13
    7:0.03
    8:0.03
    9:0.35
    10:0.02
    11:0.03
    Negative Logits
     Mata
    -3.68
     Kak
    -3.57
    ��極
    -3.48
     enslaved
    -3.43
     pigeon
    -3.32
     Sind
    -3.18
    ata
    -3.17
     embro
    -3.14
     Trap
    -3.13
     tul
    -3.12
    POSITIVE LOGITS
     review
    6.92
    review
    6.54
     Review
    6.30
     reviews
    6.16
    Review
    6.14
     reviewed
    5.84
     Reviews
    5.70
     reviewing
    5.53
     reviewer
    5.33
     reviewers
    5.27
    Activations Density 0.011%

    No Known Activations