© 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 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. 22860
    Prev
    Next
    INDEX
    Explanations

    numerical data and metrics related to performance or statistics

    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
    0:0.05
    1:0.14
    2:0.03
    3:0.04
    4:0.03
    5:0.04
    6:0.14
    7:0.04
    8:0.02
    9:0.36
    10:0.03
    11:0.03
    Negative Logits
     Bahrain
    -3.83
     Wiley
    -3.65
     Schw
    -3.61
    290
    -3.31
     Brune
    -3.25
    bryce
    -3.17
    soDeliveryDate
    -3.15
    iffs
    -3.15
    >>>>>>>>
    -3.13
     whisk
    -3.07
    POSITIVE LOGITS
    64
    6.62
     64
    6.17
     63
    4.64
    63
    4.51
     1964
    4.45
    65
    4.08
     Kard
    3.83
    Cast
    3.71
     65
    3.63
    Coin
    3.63
    Activations Density 0.005%

    No Known Activations