© 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. 15681
    Prev
    Next
    INDEX
    Explanations

    dates and timestamps

    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
    0:0.04
    1:0.03
    2:0.14
    3:0.26
    4:0.05
    5:0.04
    6:0.03
    7:0.04
    8:0.05
    9:0.03
    10:0.20
    11:0.02
    Negative Logits
    GC
    -2.63
    gnu
    -2.60
    PASS
    -2.60
    GM
    -2.58
     Di
    -2.51
    GH
    -2.47
     PG
    -2.45
    GR
    -2.43
     night
    -2.43
     Gems
    -2.43
    POSITIVE LOGITS
     Jun
    3.64
     Jul
    3.08
     Apr
    3.04
     Jan
    3.00
    Jun
    2.95
    MpServer
    2.87
     Sep
    2.83
    Jan
    2.77
    jun
    2.76
     Amend
    2.76
    Activations Density 0.001%

    No Known Activations