© 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. 10-ATT-KK
    6. 15334
    Prev
    Next
    INDEX
    Explanations

    references to regulatory guidelines or classifications related to tax-exempt organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.03
    2:0.09
    3:0.05
    4:0.04
    5:0.04
    6:0.20
    7:0.16
    8:0.02
    9:0.08
    10:0.06
    11:0.08
    Negative Logits
    bane
    -2.53
     Rodrig
    -2.44
    aptic
    -2.42
     inquest
    -2.35
    iot
    -2.32
     Nieto
    -2.31
    incial
    -2.27
     Press
    -2.25
     Roads
    -2.25
     Courier
    -2.23
    POSITIVE LOGITS
     501
    4.20
     nonprofit
    3.55
    501
    3.39
     nonprofits
    3.33
     charitable
    3.06
     tax
    2.88
     IRS
    2.73
     donors
    2.68
     donor
    2.65
     401
    2.60
    Activations Density 0.002%

    No Known Activations