© 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. 13475
    Prev
    Next
    INDEX
    Explanations

    references to tools, metrics, or rating systems

    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
    0:0.05
    1:0.07
    2:0.08
    3:0.07
    4:0.06
    5:0.04
    6:0.06
    7:0.22
    8:0.05
    9:0.06
    10:0.10
    11:0.08
    Negative Logits
     Lov
    -3.38
     ly
    -2.88
    oller
    -2.88
     TL
    -2.83
     bloom
    -2.80
     Lun
    -2.78
     Zan
    -2.76
     Lum
    -2.65
     Lauder
    -2.65
     tre
    -2.63
    POSITIVE LOGITS
     Cage
    3.33
    ettings
    3.25
    Utah
    3.22
    ACA
    2.92
     Taxi
    2.88
     Proxy
    2.85
    icho
    2.81
    anamo
    2.79
     Sahara
    2.77
    Arizona
    2.76
    Activations Density 0.001%

    No Known Activations