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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15116
    Prev
    Next
    INDEX
    Explanations

    phrases related to media and their presentation

    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
    0:0.04
    1:0.03
    2:0.04
    3:0.07
    4:0.20
    5:0.11
    6:0.07
    7:0.05
    8:0.11
    9:0.17
    10:0.03
    11:0.04
    Negative Logits
     Conclusion
    -2.31
     extortion
    -2.13
     Bridges
    -2.10
    ticket
    -2.09
     screws
    -2.04
     Prevent
    -2.04
     disadvantages
    -2.02
     Craigslist
    -2.00
     patronage
    -1.99
     actionGroup
    -1.99
    POSITIVE LOGITS
     nuance
    2.49
    DERR
    2.48
    黒
    2.25
    Iv
    2.22
    ITH
    2.13
    release
    2.03
     Remastered
    2.03
     illuminate
    2.02
     spun
    2.00
     mastered
    1.97
    Activations Density 0.001%

    No Known Activations