© 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. 486
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons or evaluations of complexity

    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
    0:0.08
    1:0.07
    2:0.06
    3:0.06
    4:0.04
    5:0.03
    6:0.22
    7:0.04
    8:0.04
    9:0.23
    10:0.04
    11:0.03
    Negative Logits
     ¯
    -3.54
     Trout
    -3.36
     Leigh
    -3.35
    marg
    -3.32
     ja
    -3.28
     Sig
    -3.27
     Peer
    -3.27
     Levi
    -3.27
     Ralph
    -3.27
     marg
    -3.21
    POSITIVE LOGITS
     Complex
    6.61
     complexes
    6.31
    complex
    5.91
     compound
    5.49
     complex
    5.38
    plex
    5.15
     compounds
    4.73
     complexity
    3.90
     Cosmos
    3.84
    MX
    3.83
    Activations Density 0.002%

    No Known Activations