© 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. 18061
    Prev
    Next
    INDEX
    Explanations

    numerical values and percentages related to statistics or records

    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
    1:0.10
    2:0.03
    3:0.04
    4:0.03
    5:0.05
    6:0.17
    7:0.04
    8:0.03
    9:0.35
    10:0.03
    11:0.04
    Negative Logits
     crow
    -4.18
     Muller
    -3.79
    Jere
    -3.66
     Reyn
    -3.58
     Zel
    -3.49
     Crow
    -3.39
     Dyn
    -3.30
     CRC
    -3.26
     Corm
    -3.20
     hierarch
    -3.19
    POSITIVE LOGITS
     85
    4.19
     65
    4.09
     105
    4.05
    ヘラ
    3.93
    105
    3.90
    65
    3.86
    115
    3.85
    85
    3.82
     75
    3.78
     115
    3.71
    Activations Density 0.017%

    No Known Activations