© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 3697
    Prev
    Next
    INDEX
    Explanations

    tax-related discussions, specifically those concerning wealth distribution and policies affecting the rich

    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
    0:0.09
    1:0.01
    2:0.16
    3:0.13
    4:0.02
    5:0.39
    6:0.01
    7:0.03
    8:0.07
    9:0.01
    10:0.02
    11:0.01
    Negative Logits
     ACLU
    -3.63
     captcha
    -3.33
    nesty
    -2.98
     bipartisan
    -2.91
     unconstitutional
    -2.85
     rescind
    -2.84
     veto
    -2.82
    constitutional
    -2.80
     legality
    -2.76
     proced
    -2.72
    POSITIVE LOGITS
     productions
    3.10
     profits
    3.08
    Owner
    2.88
    Sales
    2.66
    Produ
    2.63
    profits
    2.61
    916
    2.61
     incomes
    2.61
     dividends
    2.61
     Enterprises
    2.56
    Activations Density 0.234%

    No Known Activations