© 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. 12026
    Prev
    Next
    INDEX
    Explanations

    keywords related to technical terms in the pharmaceutical industry

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

    words related to measurement, precision, and standards in various contexts

    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
    0:0.50
    1:0.02
    2:0.03
    3:0.02
    4:0.08
    5:0.03
    6:0.08
    7:0.04
    8:0.03
    9:0.02
    10:0.07
    11:0.02
    Negative Logits
     RAD
    -1.72
     OMG
    -1.65
    assetsadobe
    -1.44
     Stewart
    -1.40
     CHRIST
    -1.37
    Reloaded
    -1.36
     Worldwide
    -1.36
     iP
    -1.33
     ROB
    -1.33
     Reborn
    -1.29
    POSITIVE LOGITS
    xual
    1.84
    pee
    1.77
    ommel
    1.76
    ippers
    1.72
    livious
    1.65
    zon
    1.65
     redes
    1.63
    dk
    1.63
    oca
    1.59
    verbs
    1.58
    Activations Density 0.421%

    No Known Activations