© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 38399
    Prev
    Next
    INDEX
    Explanations

    references to locations and residential settings

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.07
    3:0.08
    4:0.27
    5:0.02
    6:0.07
    7:0.20
    8:0.03
    9:0.03
    10:0.08
    11:0.07
    Negative Logits
    izens
    -1.86
    aughs
    -1.61
    snap
    -1.56
     physicists
    -1.55
    ifact
    -1.51
     slapped
    -1.50
    elected
    -1.46
     filmmakers
    -1.46
     fram
    -1.44
     commentators
    -1.39
    POSITIVE LOGITS
    olate
    1.83
     Manor
    1.78
     Valhalla
    1.61
    campus
    1.56
     barracks
    1.56
     spacious
    1.55
     gardens
    1.55
    omore
    1.55
    arus
    1.54
     woods
    1.54
    Activations Density 0.004%

    No Known Activations