© 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. 10-ATT-KK
    11. 17101
    Prev
    Next
    INDEX
    Explanations

    organizations and their associated activities or officials involved in significant events

    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
    1:0.02
    2:0.05
    3:0.05
    4:0.07
    5:0.47
    6:0.02
    7:0.03
    8:0.03
    9:0.11
    10:0.03
    11:0.05
    Negative Logits
     Subtle
    -2.88
     Didn
    -2.70
     outweigh
    -2.67
     outwe
    -2.66
     Enough
    -2.60
     Converted
    -2.56
     whereas
    -2.54
     Laun
    -2.51
     Leilan
    -2.45
     instead
    -2.44
    POSITIVE LOGITS
     termed
    3.75
    described
    3.45
     described
    3.40
     feared
    3.24
     asserts
    3.10
     speculated
    3.08
     contends
    3.02
     purported
    2.98
    ivably
    2.94
    idently
    2.94
    Activations Density 0.124%

    No Known Activations