© 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. 14301
    Prev
    Next
    INDEX
    Explanations

    specific phrases or sentences from news articles

    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
    0:0.10
    1:0.02
    2:0.07
    3:0.10
    4:0.05
    5:0.08
    6:0.06
    7:0.08
    8:0.07
    9:0.08
    10:0.16
    11:0.08
    Negative Logits
    ustomed
    -1.12
    iland
    -0.98
    idel
    -0.98
    pecially
    -0.97
    aundering
    -0.97
    idelity
    -0.96
    ascus
    -0.96
    BIL
    -0.94
    appropriately
    -0.94
    inged
    -0.94
    POSITIVE LOGITS
    mentioned
    0.96
     conferred
    0.95
     depends
    0.88
     extends
    0.87
     reinforces
    0.87
     justifies
    0.87
     assumes
    0.85
    \":
    0.85
     resides
    0.83
     varies
    0.83
    Activations Density 0.375%

    No Known Activations