© 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. 23345
    Prev
    Next
    INDEX
    Explanations

    elements of numerical data and specifications

    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
    0:0.03
    1:0.07
    2:0.03
    3:0.05
    4:0.03
    5:0.05
    6:0.15
    7:0.04
    8:0.03
    9:0.41
    10:0.03
    11:0.02
    Negative Logits
     Tsu
    -3.57
     Bian
    -3.50
    patch
    -3.36
     Mare
    -3.27
    bid
    -3.26
     Sau
    -3.22
     Amar
    -3.21
    arity
    -3.20
     Maur
    -3.18
    au
    -3.17
    POSITIVE LOGITS
    60
    5.42
     60
    4.86
    1960
    4.19
     caric
    4.16
     1860
    4.09
     1960
    4.06
    59
    3.51
     Ghana
    3.49
    61
    3.48
     Gingrich
    3.41
    Activations Density 0.007%

    No Known Activations