© 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. 43608
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to categorical definitions and classifications

    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
    0:0.03
    1:0.02
    2:0.04
    3:0.05
    4:0.09
    5:0.03
    6:0.06
    7:0.40
    8:0.03
    9:0.03
    10:0.10
    11:0.07
    Negative Logits
     webcam
    -1.52
     lining
    -1.35
     swayed
    -1.32
     breeze
    -1.29
     Provided
    -1.28
     Printed
    -1.28
     withstand
    -1.23
     Joh
    -1.20
     hopping
    -1.20
    ..........
    -1.20
    POSITIVE LOGITS
    raph
    1.56
    grave
    1.50
     coined
    1.50
    Accessory
    1.50
     gener
    1.45
    tera
    1.44
    amphetamine
    1.41
    non
    1.41
    hani
    1.38
    opa
    1.38
    Activations Density 0.013%

    No Known Activations