© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 8024
    Prev
    Next
    INDEX
    Explanations

    comparative phrases highlighting contrasts or conflicting ideas

    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
    1:0.16
    2:0.03
    3:0.03
    4:0.10
    5:0.02
    6:0.04
    7:0.36
    8:0.03
    9:0.03
    10:0.04
    11:0.08
    Negative Logits
    Nut
    -2.76
    Failure
    -2.46
    upper
    -2.37
     Homeless
    -2.33
     Wr
    -2.30
     Broken
    -2.30
     Fail
    -2.28
     poorest
    -2.25
     Improved
    -2.24
    PN
    -2.23
    POSITIVE LOGITS
    isi
    2.88
     Metatron
    2.86
    etheus
    2.57
     Miranda
    2.51
     projector
    2.50
    unci
    2.47
    issions
    2.44
     extradition
    2.38
    quez
    2.37
    uploads
    2.36
    Activations Density 0.020%

    No Known Activations