© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 24164
    Prev
    Next
    INDEX
    Explanations

    references to periods of time and their qualitative significance

    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
    0:0.09
    1:0.04
    2:0.06
    3:0.04
    4:0.06
    5:0.04
    6:0.23
    7:0.05
    8:0.10
    9:0.17
    10:0.03
    11:0.03
    Negative Logits
    inki
    -4.60
    oop
    -3.95
    š
    -3.66
     Sai
    -3.58
    yk
    -3.47
     boobs
    -3.42
    urdue
    -3.38
    enegger
    -3.36
    Sav
    -3.32
    ptr
    -3.27
    POSITIVE LOGITS
     Mercury
    10.66
    Merc
    10.24
     Merc
    7.55
     mercury
    7.06
     merc
    6.36
     Hermes
    5.03
     Neptune
    4.59
     Hawth
    4.58
     Miner
    4.57
     Avalon
    4.56
    Activations Density 0.003%

    No Known Activations