© 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. 4135
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and judicial proceedings

    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
    0:0.05
    1:0.04
    2:0.09
    3:0.15
    4:0.09
    5:0.03
    6:0.02
    7:0.15
    8:0.03
    9:0.01
    10:0.26
    11:0.03
    Negative Logits
    erto
    -2.41
     lately
    -2.11
     OECD
    -2.05
     renaissance
    -2.03
    ighton
    -2.03
    pport
    -1.97
    Quantity
    -1.96
    aido
    -1.96
     dividend
    -1.96
     Historically
    -1.90
    POSITIVE LOGITS
     proceeded
    4.06
    Eventually
    3.99
     ensued
    3.84
     eventually
    3.70
     subsequently
    3.57
    later
    3.48
     promptly
    3.43
     thereafter
    3.40
     afterward
    3.35
    sequently
    3.34
    Activations Density 0.832%

    No Known Activations