© 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. 5-ATT-KK
    11. 43745
    Prev
    Next
    INDEX
    Explanations

    numerical data and quantities related to events or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.17
    3:0.04
    4:0.17
    5:0.02
    6:0.24
    7:0.10
    8:0.05
    9:0.03
    10:0.05
    11:0.04
    Negative Logits
    bnb
    -1.62
    taboola
    -1.59
     alone
    -1.59
    inventoryQuantity
    -1.52
    itives
    -1.46
    quickShipAvailable
    -1.41
    soType
    -1.41
    ptroller
    -1.38
     perceive
    -1.31
    ��
    -1.30
    POSITIVE LOGITS
    Tuesday
    1.15
     Saunders
    1.10
     seism
    1.10
     Warsaw
    1.10
     Airways
    1.09
     Trace
    1.09
     pending
    1.08
    Feature
    1.07
    Balt
    1.06
     Jazeera
    1.06
    Activations Density 0.004%

    No Known Activations