© 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. 9-ATT-KK
    11. 2053
    Prev
    Next
    INDEX
    Explanations

    instances of the conjunction "and" in various constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.17
    2:0.05
    3:0.09
    4:0.07
    5:0.07
    6:0.05
    7:0.09
    8:0.04
    9:0.06
    10:0.05
    11:0.15
    Negative Logits
     Nept
    -2.82
     Dwell
    -2.68
     Quality
    -2.51
     Its
    -2.46
     Rated
    -2.46
    ��
    -2.25
     Sit
    -2.25
     Overs
    -2.24
     Own
    -2.23
     Wanted
    -2.21
    POSITIVE LOGITS
    see
    2.60
    irtual
    2.24
     circumcised
    2.23
    verbal
    2.20
    Baltimore
    2.16
     appendix
    2.13
     derog
    2.12
    ardless
    2.12
    indal
    2.10
    ivably
    2.06
    Activations Density 0.000%

    No Known Activations