© 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. 18254
    Prev
    Next
    INDEX
    Explanations

    references to organizational structure or frameworks

    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
    0:0.04
    1:0.03
    2:0.11
    3:0.08
    4:0.06
    5:0.04
    6:0.06
    7:0.04
    8:0.04
    9:0.07
    10:0.25
    11:0.14
    Negative Logits
     declass
    -1.47
     incrim
    -1.44
     convinc
    -1.43
    nsics
    -1.38
     sten
    -1.37
     resemb
    -1.34
    abal
    -1.32
    aspers
    -1.31
    andestine
    -1.27
    hop
    -1.26
    POSITIVE LOGITS
    taboola
    1.90
    =#
    1.63
    duration
    1.63
    ��極
    1.62
    Duration
    1.55
     Duration
    1.51
    Requires
    1.45
    魔
    1.36
     {*
    1.36
     discretionary
    1.34
    Activations Density 0.000%

    No Known Activations