© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 236
    Prev
    Next
    INDEX
    Explanations

    relative pronouns and clauses that refer back to nouns

    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
    0:0.01
    1:0.02
    2:0.14
    3:0.04
    4:0.08
    5:0.03
    6:0.03
    7:0.43
    8:0.02
    9:0.03
    10:0.04
    11:0.06
    Negative Logits
    agall
    -1.97
    erg
    -1.83
    ukemia
    -1.76
     decency
    -1.69
    itely
    -1.66
    raph
    -1.65
    iku
    -1.63
     anonymity
    -1.57
    seys
    -1.56
    Mem
    -1.56
    POSITIVE LOGITS
    ��
    1.63
     quickest
    1.62
    ◼
    1.60
     uncovered
    1.57
     catapult
    1.57
     hurled
    1.50
     untold
    1.48
     undis
    1.47
     recorded
    1.47
    rists
    1.44
    Activations Density 0.059%

    No Known Activations