© 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. 5-ATT-KK
    11. 43464
    Prev
    Next
    INDEX
    Explanations

    function declaration patterns in programming syntax

    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
    0:0.10
    1:0.32
    2:0.04
    3:0.05
    4:0.03
    5:0.17
    6:0.04
    7:0.01
    8:0.03
    9:0.07
    10:0.04
    11:0.05
    Negative Logits
    sburg
    -2.00
    akia
    -1.98
    oshenko
    -1.80
    monds
    -1.76
    angel
    -1.67
    shaw
    -1.65
    acho
    -1.62
     annexed
    -1.62
    jab
    -1.60
    igh
    -1.58
    POSITIVE LOGITS
     func
    2.26
    soDeliveryDate
    2.18
    function
    2.12
     function
    2.06
     Mechdragon
    2.06
    Collection
    1.99
    collection
    1.92
    rolet
    1.89
    Listener
    1.88
     Procedure
    1.86
    Activations Density 0.002%

    No Known Activations