© 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. 3-ATT-KK
    6. 10902
    Prev
    Next
    INDEX
    Explanations

    terms related to services and agreements, often in legal or financial 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
    0:0.02
    1:0.02
    2:0.07
    3:0.09
    4:0.02
    5:0.05
    6:0.10
    7:0.33
    8:0.06
    9:0.03
    10:0.08
    11:0.07
    Negative Logits
    lege
    -1.46
    ovych
    -1.35
    rosis
    -1.28
     Poe
    -1.25
    ukemia
    -1.09
    obin
    -1.07
     Syndrome
    -1.06
    ocular
    -1.06
    bole
    -1.05
    roth
    -1.05
    POSITIVE LOGITS
    Services
    1.18
     warranties
    1.14
     Directorate
    1.13
     licences
    1.12
    ��
    1.09
     payroll
    1.08
     ministries
    1.07
    ��極
    1.06
     tariffs
    1.05
     Quran
    1.03
    Activations Density 0.043%

    No Known Activations