© 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. 9-ATT-KK
    11. 9722
    Prev
    Next
    INDEX
    Explanations

    references to statistics or numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.44
    2:0.04
    3:0.09
    4:0.05
    5:0.05
    6:0.05
    7:0.05
    8:0.02
    9:0.08
    10:0.03
    11:0.02
    Negative Logits
    soType
    -2.62
    catentry
    -2.48
    aval
    -2.40
    plin
    -2.39
    isSpecialOrderable
    -2.38
    DN
    -2.37
    ammers
    -2.37
    abbage
    -2.33
    gae
    -2.27
    emp
    -2.21
    POSITIVE LOGITS
    five
    6.49
     fourteen
    6.29
     seven
    6.28
    seven
    6.22
     six
    6.21
     five
    6.19
     eight
    6.16
    six
    6.03
     fifteen
    5.98
     four
    5.90
    Activations Density 0.170%

    No Known Activations