© 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. 13518
    Prev
    Next
    INDEX
    Explanations

    terms related to statistics and demographics

    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
    2:0.02
    3:0.04
    4:0.07
    5:0.06
    6:0.02
    7:0.05
    8:0.03
    9:0.52
    10:0.02
    11:0.07
    Negative Logits
     instructions
    -2.19
     adjustments
    -2.13
     myself
    -2.01
     instincts
    -2.00
    llah
    -2.00
     versus
    -1.97
     geometry
    -1.97
     stabilization
    -1.96
     placement
    -1.95
    iets
    -1.95
    POSITIVE LOGITS
    htaking
    2.61
    famous
    2.46
    isable
    2.37
    orious
    2.34
    icipated
    2.34
    inently
    2.32
    roversial
    2.28
    ivated
    2.27
    ceivable
    2.27
    inguished
    2.27
    Activations Density 0.063%

    No Known Activations