© 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. 7070
    Prev
    Next
    INDEX
    Explanations

    quotes and phrases that indicate planned actions or proposed standards

    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
    1:0.43
    2:0.03
    3:0.08
    4:0.04
    5:0.03
    6:0.05
    7:0.09
    8:0.07
    9:0.04
    10:0.02
    11:0.04
    Negative Logits
    Complete
    -2.78
    abetic
    -2.74
    arb
    -2.62
    olescent
    -2.54
     Cancel
    -2.53
    alde
    -2.46
    Sax
    -2.46
    Sav
    -2.45
     Haste
    -2.43
    Skip
    -2.42
    POSITIVE LOGITS
     inside
    7.67
    inside
    7.47
     Inside
    7.39
    Inside
    7.37
    outside
    7.16
     outside
    7.01
     Outside
    6.85
    Outside
    6.05
     inner
    4.53
    external
    4.40
    Activations Density 0.184%

    No Known Activations