© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3648
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental regulations and permits for industrial activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.01
    2:0.10
    3:0.22
    4:0.02
    5:0.14
    6:0.01
    7:0.05
    8:0.06
    9:0.01
    10:0.22
    11:0.03
    Negative Logits
     professionalism
    -2.04
     professionals
    -1.92
    umbledore
    -1.87
     satisfaction
    -1.85
     verbal
    -1.82
    ploma
    -1.76
    iquette
    -1.73
    erning
    -1.73
     attentive
    -1.73
     bravery
    -1.70
    POSITIVE LOGITS
     southwest
    2.42
     northwest
    2.40
     offshore
    2.32
     southeast
    2.28
     wetlands
    2.23
     south
    2.23
     downstream
    2.20
     unused
    2.18
     northeast
    2.17
     north
    2.17
    Activations Density 0.247%

    No Known Activations