© 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. 3265
    Prev
    Next
    INDEX
    Explanations

    references to academic or professional classification and identifiers, particularly in a coding or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.12
    1:0.31
    2:0.05
    3:0.04
    4:0.04
    5:0.15
    6:0.04
    7:0.02
    8:0.05
    9:0.05
    10:0.04
    11:0.04
    Negative Logits
    rush
    -1.68
    Downloadha
    -1.67
    izu
    -1.56
    luaj
    -1.55
    REM
    -1.54
    hiro
    -1.52
    黒
    -1.52
    yip
    -1.50
    ripp
    -1.49
     UFO
    -1.49
    POSITIVE LOGITS
    class
    2.63
     class
    2.29
     Class
    2.26
    Class
    2.00
     CLASS
    1.92
     sergeant
    1.68
     Classes
    1.67
     subclass
    1.66
     Vendor
    1.66
     Christine
    1.60
    Activations Density 0.003%

    No Known Activations