© 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. 10-ATT-KK
    11. 9098
    Prev
    Next
    INDEX
    Explanations

    terms related to taxation and income distribution

    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
    0:0.05
    1:0.06
    2:0.05
    3:0.14
    4:0.03
    5:0.04
    6:0.04
    7:0.05
    8:0.32
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
    acked
    -2.34
    wcs
    -2.18
    iqu
    -2.17
    iov
    -2.16
    ounced
    -2.15
    iac
    -2.06
     pneum
    -2.06
    ived
    -2.02
     subp
    -1.95
    oke
    -1.93
    POSITIVE LOGITS
     after
    4.63
    after
    4.36
     AFTER
    4.30
    After
    4.17
     After
    4.16
     BEFORE
    3.88
     before
    3.73
    before
    3.60
    Before
    3.41
     afterward
    3.38
    Activations Density 0.016%

    No Known Activations