© 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. 13697
    Prev
    Next
    INDEX
    Explanations

    instructions and descriptions related to software usage, particularly focusing on patterns and filtering options

    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
    0:0.12
    1:0.08
    2:0.06
    3:0.09
    4:0.07
    5:0.02
    6:0.10
    7:0.14
    8:0.03
    9:0.03
    10:0.06
    11:0.15
    Negative Logits
     Monteneg
    -2.50
    LV
    -2.46
     ►
    -2.41
    ‎
    -2.40
     Karn
    -2.39
    bum
    -2.31
     Governors
    -2.24
     Clarkson
    -2.21
     Mali
    -2.17
     Vide
    -2.17
    POSITIVE LOGITS
    pattern
    5.37
     Pattern
    5.18
    Pattern
    5.13
     pattern
    5.08
     patterns
    4.88
     Patterns
    4.62
     crochet
    3.27
     regex
    3.22
     motif
    3.10
     repeats
    3.09
    Activations Density 0.026%

    No Known Activations