© 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. 147
    Prev
    Next
    INDEX
    Explanations

    references to delegations and their activities or compositions

    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
    1:0.01
    2:0.06
    3:0.05
    4:0.05
    5:0.03
    6:0.03
    7:0.25
    8:0.05
    9:0.04
    10:0.27
    11:0.08
    Negative Logits
     slash
    -1.73
     sentence
    -1.60
     Runes
    -1.59
     compounded
    -1.59
     impover
    -1.56
     tragedies
    -1.54
    conom
    -1.52
     refin
    -1.51
     suicides
    -1.50
     karma
    -1.49
    POSITIVE LOGITS
    assadors
    1.96
     delegation
    1.94
     assembled
    1.88
     comr
    1.81
    assador
    1.77
    accompanied
    1.76
     representatives
    1.73
     deleg
    1.70
    ilion
    1.68
    Rus
    1.65
    Activations Density 0.003%

    No Known Activations