© 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. 20716
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical thresholds and significant figures

    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
    1:0.19
    2:0.09
    3:0.05
    4:0.06
    5:0.03
    6:0.10
    7:0.07
    8:0.03
    9:0.03
    10:0.11
    11:0.11
    Negative Logits
     Mongol
    -3.29
     Rev
    -2.85
    GN
    -2.82
     Kis
    -2.77
     Tripoli
    -2.66
     Biol
    -2.66
     Semin
    -2.60
     Bras
    -2.59
     Bristol
    -2.59
     Franklin
    -2.58
    POSITIVE LOGITS
     threshold
    6.49
     thresholds
    6.24
    reshold
    4.94
    trigger
    3.46
    limits
    3.37
     triggers
    3.37
    Trigger
    3.31
     cutoff
    3.21
     Trigger
    3.18
     trigger
    3.15
    Activations Density 0.001%

    No Known Activations