© 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. 13576
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to analysis and categorization of information

    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
    0:0.03
    1:0.03
    2:0.04
    3:0.04
    4:0.06
    5:0.30
    6:0.03
    7:0.04
    8:0.03
    9:0.23
    10:0.03
    11:0.10
    Negative Logits
    until
    -3.39
    required
    -2.90
     fearing
    -2.63
    obil
    -2.60
    optional
    -2.59
    possibly
    -2.56
    secure
    -2.55
    thinkable
    -2.47
    unless
    -2.45
    bidden
    -2.45
    POSITIVE LOGITS
     trends
    3.17
     versus
    3.03
     correlations
    2.75
     graphs
    2.71
     similarities
    2.59
     nowadays
    2.58
     analogy
    2.53
     comparisons
    2.53
     equivalents
    2.51
     percentages
    2.40
    Activations Density 0.040%

    No Known Activations