© 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. 20174
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between characters and their backgrounds

    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
    2:0.03
    3:0.09
    4:0.15
    5:0.31
    6:0.05
    7:0.07
    8:0.03
    9:0.08
    10:0.02
    11:0.07
    Negative Logits
    Conclusion
    -3.82
     Whilst
    -3.53
    sic
    -3.50
     Conclusion
    -3.34
     Alternatively
    -3.26
    Furthermore
    -3.26
    Summary
    -3.25
     Invalid
    -3.15
     Furthermore
    -3.09
    Alternatively
    -3.05
    POSITIVE LOGITS
     grew
    4.29
     remembers
    3.68
     bonded
    3.46
     dreamed
    3.46
     recalls
    3.31
     sprang
    3.30
     watched
    3.29
     wore
    3.27
    Enlarge
    3.26
     drove
    3.25
    Activations Density 0.644%

    No Known Activations