© 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. 9-ATT-KK
    11. 2042
    Prev
    Next
    INDEX
    Explanations

    terms related to symbols and their meanings

    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
    0:0.11
    1:0.06
    2:0.07
    3:0.06
    4:0.04
    5:0.05
    6:0.19
    7:0.04
    8:0.06
    9:0.21
    10:0.03
    11:0.02
    Negative Logits
    Wi
    -3.88
     Utt
    -3.74
     KS
    -3.72
    itia
    -3.66
     Greene
    -3.65
     Kis
    -3.57
     Lon
    -3.52
     Decker
    -3.49
     Grassley
    -3.40
    Cook
    -3.31
    POSITIVE LOGITS
     symbol
    8.13
     symbols
    7.75
     Symb
    7.63
     Symbol
    7.47
     symbolic
    5.45
     symbolism
    5.36
     emblem
    5.21
    mbol
    5.16
     glyph
    4.45
     symb
    4.40
    Activations Density 0.003%

    No Known Activations