© 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. 3-ATT-KK
    11. 13590
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial calculations and business figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    statistical calculations and financial metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.10
    3:0.08
    4:0.01
    5:0.06
    6:0.06
    7:0.14
    8:0.10
    9:0.17
    10:0.07
    11:0.12
    Negative Logits
    Introduced
    -1.18
     breat
    -1.11
    idated
    -1.11
    apers
    -1.10
     rallied
    -1.08
    arak
    -1.04
    ?????
    -1.02
     visibly
    -1.01
    ilyn
    -1.00
    osponsors
    -1.00
    POSITIVE LOGITS
     calculating
    1.34
     probabilities
    1.32
     Calculator
    1.26
     Profit
    1.16
    verages
    1.14
     Median
    1.09
     graph
    1.08
     Distribution
    1.07
     mund
    1.07
     percentile
    1.07
    Activations Density 0.019%

    No Known Activations