© 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. 16003
    Prev
    Next
    INDEX
    Explanations

    references to government-related policies and financial matters

    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
    0:0.08
    1:0.02
    2:0.04
    3:0.19
    4:0.05
    5:0.04
    6:0.09
    7:0.04
    8:0.04
    9:0.09
    10:0.15
    11:0.10
    Negative Logits
     Tucker
    -2.81
    kward
    -2.71
     pouch
    -2.67
     bait
    -2.63
     sleeve
    -2.62
     combos
    -2.60
     combo
    -2.57
    osite
    -2.56
     fuzz
    -2.53
    yne
    -2.49
    POSITIVE LOGITS
    �
    5.37
    ■
    4.08
    �
    3.90
     �
    3.60
    vernment
    3.57
    ‎
    3.53
    Ranked
    3.50
    national
    3.26
    India
    3.23
    Population
    3.21
    Activations Density 0.121%

    No Known Activations