© 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. 6852
    Prev
    Next
    INDEX
    Explanations

    phrases related to future prospects and innovation

    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
    2:0.04
    3:0.06
    4:0.05
    5:0.34
    6:0.02
    7:0.03
    8:0.02
    9:0.27
    10:0.02
    11:0.07
    Negative Logits
     consistently
    -3.01
     additionally
    -2.96
     regularly
    -2.76
     extensively
    -2.65
     inconsist
    -2.64
     routinely
    -2.58
     constantly
    -2.58
     lately
    -2.57
     withheld
    -2.56
     derog
    -2.56
    POSITIVE LOGITS
     awaits
    4.27
    \":
    3.08
     looms
    3.05
    !
    2.90
     welcomes
    2.85
     await
    2.84
     begins
    2.77
    !'
    2.75
     Renaissance
    2.71
    !]
    2.71
    Activations Density 0.319%

    No Known Activations