© 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. 20289
    Prev
    Next
    INDEX
    Explanations

    references to tax-exempt organizations and their classifications under specific IRS codes

    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
    0:0.43
    1:0.01
    2:0.10
    3:0.13
    4:0.02
    5:0.08
    6:0.02
    7:0.04
    8:0.03
    9:0.01
    10:0.06
    11:0.02
    Negative Logits
     Pear
    -2.40
     GeForce
    -2.34
     Jord
    -2.28
    Tube
    -2.19
    rosse
    -2.19
     loudspe
    -2.17
     Ake
    -2.17
     Bridges
    -2.13
     Teg
    -2.10
    agons
    -2.10
    POSITIVE LOGITS
     charitable
    3.22
     nonprofits
    3.07
     nonprofit
    3.04
     501
    2.76
     charity
    2.50
     tax
    2.48
     donation
    2.44
     organis
    2.44
    DIV
    2.42
     IRS
    2.35
    Activations Density 0.005%

    No Known Activations