© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-ATT-KK
    11. 19644
    Prev
    Next
    INDEX
    Explanations

    references to significant expansions or developments in entertainment, specifically related to announcements and financial contributions

    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
    0:0.17
    1:0.03
    2:0.16
    3:0.06
    4:0.04
    5:0.06
    6:0.11
    7:0.05
    8:0.09
    9:0.12
    10:0.03
    11:0.04
    Negative Logits
     lapt
    -3.82
    Williams
    -3.70
     retri
    -3.69
     Watkins
    -3.54
     Seym
    -3.27
     lap
    -3.16
    isconsin
    -3.09
     ther
    -3.09
     chemistry
    -3.06
     brake
    -3.04
    POSITIVE LOGITS
     Expansion
    8.11
     expansions
    7.20
     expansion
    7.13
    exp
    5.06
     Expand
    5.01
     expand
    4.99
    Exp
    4.83
     expands
    4.61
     expanded
    4.56
     expanding
    4.52
    Activations Density 0.006%

    No Known Activations