© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 12264
    Prev
    Next
    INDEX
    Explanations

    terms related to physical health and well-being

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

    concepts related to well-being and health

    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
    0:0.03
    1:0.02
    2:0.21
    3:0.05
    4:0.02
    5:0.02
    6:0.05
    7:0.09
    8:0.15
    9:0.19
    10:0.07
    11:0.07
    Negative Logits
    Latin
    -1.16
     converter
    -1.12
     roundup
    -1.05
     naming
    -1.05
    lot
    -1.05
    elf
    -1.02
    Ger
    -1.01
     tooltip
    -1.01
     rendition
    -1.00
    ource
    -0.99
    POSITIVE LOGITS
     forever
    1.26
     Marketable
    1.20
    arsity
    1.20
    ACTED
    1.19
    ienced
    1.13
    urized
    1.13
    angered
    1.12
     indefinitely
    1.10
    active
    1.09
    oped
    1.09
    Activations Density 0.028%

    No Known Activations