© 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 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. 21012
    Prev
    Next
    INDEX
    Explanations

    content related to software compatibility and operating systems

    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
    0:0.07
    1:0.03
    2:0.05
    3:0.05
    4:0.06
    5:0.03
    6:0.03
    7:0.37
    8:0.01
    9:0.04
    10:0.04
    11:0.16
    Negative Logits
     Stev
    -2.65
    Georgia
    -2.59
     Perth
    -2.40
     Georgia
    -2.40
     Sunderland
    -2.35
    Seattle
    -2.26
     Winston
    -2.25
     Seahawks
    -2.22
     Mariners
    -2.19
     Hend
    -2.19
    POSITIVE LOGITS
    nai
    2.56
    ravings
    2.33
     Handler
    2.27
     Ai
    2.23
    ombies
    2.17
    anim
    2.13
    iple
    2.11
     Rapt
    2.06
     Finder
    2.06
    loader
    2.02
    Activations Density 0.043%

    No Known Activations