© 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. 13582
    Prev
    Next
    INDEX
    Explanations

    phrases indicating fixes or bugs in software, particularly related to crashes and game mechanics

    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
    1:0.09
    2:0.06
    3:0.06
    4:0.14
    5:0.07
    6:0.05
    7:0.16
    8:0.07
    9:0.09
    10:0.05
    11:0.05
    Negative Logits
     [...]
    -2.26
     driveway
    -2.21
     drives
    -2.08
    EMA
    -2.08
     indo
    -2.06
    akeru
    -2.05
    paralle
    -1.99
    nsics
    -1.98
     TAM
    -1.96
    ,''
    -1.96
    POSITIVE LOGITS
     Fixed
    4.04
    Fixed
    3.89
     fixed
    3.36
     Changed
    3.28
     Fixes
    3.23
     Reduced
    3.12
    Improved
    3.12
     corrected
    3.06
     Added
    3.06
     Improved
    3.06
    Activations Density 0.011%

    No Known Activations