© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 36127
    Prev
    Next
    INDEX
    Explanations

    specific nouns and pronouns related to people and their roles or identities

    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
    1:0.43
    2:0.02
    3:0.02
    4:0.02
    5:0.15
    6:0.02
    7:0.01
    8:0.05
    9:0.06
    10:0.03
    11:0.02
    Negative Logits
    mson
    -1.59
    nell
    -1.52
    hw
    -1.47
    Tweet
    -1.46
    hra
    -1.45
    grey
    -1.43
    Marginal
    -1.43
    Hu
    -1.41
    bryce
    -1.40
    pless
    -1.39
    POSITIVE LOGITS
     is
    2.14
    is
    1.86
     Is
    1.82
     exists
    1.72
     interven
    1.71
     does
    1.71
     persists
    1.70
     IS
    1.65
     guid
    1.63
     governs
    1.61
    Activations Density 0.101%

    No Known Activations