© 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. 45126
    Prev
    Next
    INDEX
    Explanations

    references to location and community context

    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
    1:0.01
    2:0.08
    3:0.08
    4:0.14
    5:0.04
    6:0.04
    7:0.09
    8:0.05
    9:0.05
    10:0.29
    11:0.06
    Negative Logits
     enz
    -1.76
    finger
    -1.68
     mitochondrial
    -1.68
     recourse
    -1.61
     antitrust
    -1.60
     chromos
    -1.60
     ovarian
    -1.59
     chromosomes
    -1.59
     subset
    -1.57
    metics
    -1.54
    POSITIVE LOGITS
     humble
    1.79
    build
    1.71
     Dwell
    1.70
    atown
    1.67
     creeps
    1.66
    owntown
    1.59
    elaide
    1.52
    Builder
    1.50
     Unch
    1.50
    hov
    1.49
    Activations Density 0.021%

    No Known Activations