© 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. 8422
    Prev
    Next
    INDEX
    Explanations

    numerical values related to stats and attributes in a gaming context

    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
    0:0.08
    1:0.06
    2:0.08
    3:0.08
    4:0.07
    5:0.16
    6:0.03
    7:0.09
    8:0.08
    9:0.10
    10:0.06
    11:0.05
    Negative Logits
     todd
    -2.58
     wouldn
    -2.54
    oln
    -2.50
     imaginable
    -2.50
    peat
    -2.48
     unsu
    -2.45
     unfit
    -2.40
     ought
    -2.35
     ensu
    -2.35
     suffice
    -2.33
    POSITIVE LOGITS
     Deals
    2.95
     Enemies
    2.88
     Travels
    2.63
    Deal
    2.63
     Amount
    2.62
    Increase
    2.57
     Adren
    2.48
     Prev
    2.46
     Increase
    2.45
    Increases
    2.44
    Activations Density 0.001%

    No Known Activations