© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 12523
    Prev
    Next
    INDEX
    Explanations

    references to tax avoidance and corporate tax practices

    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
    0:0.44
    1:0.01
    2:0.16
    3:0.09
    4:0.02
    5:0.11
    6:0.01
    7:0.03
    8:0.04
    9:0.01
    10:0.03
    11:0.00
    Negative Logits
    journal
    -2.49
    pict
    -2.33
     Sebast
    -2.28
     IMAGES
    -2.23
     hasht
    -2.17
     durability
    -2.14
     firmware
    -2.08
     Telegram
    -2.04
     goggles
    -2.04
     VID
    -2.02
    POSITIVE LOGITS
     levied
    3.47
     tax
    3.29
    Tax
    3.26
     levy
    3.14
     taxing
    3.07
     taxes
    3.05
     Revenue
    2.87
    tax
    2.87
     taxed
    2.81
     taxation
    2.81
    Activations Density 0.312%

    No Known Activations