© 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. 9974
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of production processes and industrial activities

    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
    1:0.05
    2:0.12
    3:0.05
    4:0.02
    5:0.08
    6:0.07
    7:0.10
    8:0.20
    9:0.08
    10:0.08
    11:0.09
    Negative Logits
    jri
    -1.09
    amaz
    -1.08
    _-
    -1.05
    twitter
    -1.04
    ilogy
    -1.01
     0004
    -1.01
    orio
    -0.96
    rontal
    -0.96
    �
    -0.95
    ieg
    -0.95
    POSITIVE LOGITS
     purposes
    1.63
     environments
    1.28
     contexts
    1.17
     climates
    1.16
     laboratories
    1.16
     quantities
    1.14
     bulk
    1.14
     manufacture
    1.14
     experiments
    1.13
     regimes
    1.06
    Activations Density 0.077%

    No Known Activations