© 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. 15868
    Prev
    Next
    INDEX
    Explanations

    constructive feedback and discussions about user experiences

    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
    0:0.06
    1:0.04
    2:0.05
    3:0.04
    4:0.14
    5:0.03
    6:0.15
    7:0.16
    8:0.03
    9:0.08
    10:0.04
    11:0.12
    Negative Logits
     extrad
    -2.69
     extradition
    -2.49
     impeachment
    -2.42
     barred
    -2.34
     seizure
    -2.33
     subtitle
    -2.33
    ibrary
    -2.32
     shuffle
    -2.30
     disguise
    -2.30
     pretended
    -2.29
    POSITIVE LOGITS
     feedback
    5.28
     Feedback
    4.63
     testers
    3.50
     constructive
    3.32
    Feed
    3.12
     input
    3.04
     Customer
    2.98
     vibration
    2.98
     reviews
    2.83
     critiques
    2.80
    Activations Density 0.013%

    No Known Activations