© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 23290
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements of items, often related to various aspects like productivity, data, and goods

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

    phrases emphasizing quantity and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.03
    2:0.21
    3:0.04
    4:0.24
    5:0.06
    6:0.02
    7:0.03
    8:0.09
    9:0.13
    10:0.04
    11:0.02
    Negative Logits
    Pod
    -1.50
     Khalid
    -1.41
    \\\\\\\\
    -1.36
     Dhabi
    -1.35
    Chel
    -1.32
    ��
    -1.30
    Ell
    -1.30
     Lumpur
    -1.29
     Zucker
    -1.27
     Bark
    -1.27
    POSITIVE LOGITS
     quantities
    1.70
     goods
    1.55
    uties
    1.49
    emort
    1.40
     loads
    1.40
     labou
    1.39
     arsen
    1.38
     surplus
    1.38
     quantity
    1.38
     crops
    1.37
    Activations Density 0.002%

    No Known Activations