© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 12431
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming code and specific functions within the code

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.05
    1:0.07
    2:0.14
    3:0.05
    4:0.10
    5:0.08
    6:0.04
    7:0.05
    8:0.06
    9:0.22
    10:0.07
    11:0.03
    Negative Logits
    jri
    -1.56
    ebus
    -1.50
     resil
    -1.47
     SAF
    -1.37
    EED
    -1.36
    ticket
    -1.32
    )</
    -1.31
     Reloaded
    -1.31
    egu
    -1.30
    massive
    -1.30
    POSITIVE LOGITS
     noun
    1.82
     phrases
    1.62
    Latin
    1.59
     narrator
    1.55
     verse
    1.55
    š
    1.51
     Hindi
    1.49
     verbs
    1.48
     greeting
    1.45
     denotes
    1.43
    Activations Density 0.008%

    No Known Activations