© 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. 23927
    Prev
    Next
    INDEX
    Explanations

    references to arguments and the necessity of certain conditions or actions

    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
    0:0.04
    1:0.41
    2:0.05
    3:0.04
    4:0.05
    5:0.05
    6:0.03
    7:0.08
    8:0.03
    9:0.05
    10:0.08
    11:0.03
    Negative Logits
    abouts
    -3.11
    umbnails
    -2.99
    reenshots
    -2.76
    arij
    -2.71
    ecause
    -2.68
    ibliography
    -2.66
    oother
    -2.58
    lique
    -2.39
    uilt
    -2.33
    rolled
    -2.32
    POSITIVE LOGITS
     must
    6.16
    must
    5.62
     MUST
    4.87
    Must
    4.81
     Must
    4.56
     cannot
    3.77
    required
    3.33
     Required
    3.29
     required
    3.15
     need
    3.00
    Activations Density 0.055%

    No Known Activations