© 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. 10-ATT-KK
    11. 16248
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "and" and related conjunctions and connectors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.03
    2:0.06
    3:0.05
    4:0.47
    5:0.05
    6:0.02
    7:0.06
    8:0.06
    9:0.05
    10:0.03
    11:0.04
    Negative Logits
    ?'
    -4.43
    .'
    -4.18
    ,'
    -4.16
    !'
    -4.03
    )'
    -3.90
    ‐
    -3.48
    ]'
    -3.24
    ').
    -3.11
    '),
    -2.98
    ‑
    -2.83
    POSITIVE LOGITS
     "
    8.25
     ".
    8.11
     "'
    8.03
     "...
    7.70
     "…
    7.64
     "[
    7.55
     ",
    7.45
     "(
    7.25
     "+
    6.62
     "-
    6.52
    Activations Density 0.608%

    No Known Activations