© 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. 16177
    Prev
    Next
    INDEX
    Explanations

    details related to locations, properties, and demographics

    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
    0:0.03
    1:0.02
    2:0.02
    3:0.06
    4:0.07
    5:0.16
    6:0.03
    7:0.05
    8:0.01
    9:0.42
    10:0.01
    11:0.07
    Negative Logits
    irms
    -2.46
    actic
    -2.27
    arios
    -2.09
    activ
    -2.06
    20439
    -2.05
    PLA
    -2.04
    azeera
    -2.04
    AUD
    -2.00
    instein
    -2.00
     Cancel
    -1.99
    POSITIVE LOGITS
     housed
    3.53
    Located
    3.38
     situated
    3.34
     tucked
    3.31
     perched
    3.19
     Located
    3.19
     located
    3.19
     surrounded
    3.09
     where
    3.06
    Built
    2.99
    Activations Density 1.423%

    No Known Activations