© 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. 285
    Prev
    Next
    INDEX
    Explanations

    references to influential individuals and their philosophies or qualities

    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
    0:0.02
    1:0.00
    2:0.13
    3:0.11
    4:0.09
    5:0.07
    6:0.01
    7:0.04
    8:0.09
    9:0.10
    10:0.15
    11:0.11
    Negative Logits
     decrease
    -1.06
    ‐
    -1.04
    ynchron
    -1.04
    ystem
    -1.03
    xf
    -1.02
    forcement
    -1.00
    ophysical
    -0.98
    oton
    -0.97
    ouls
    -0.97
    nw
    -0.97
    POSITIVE LOGITS
     persona
    1.34
     himself
    1.24
     Himself
    1.23
    Born
    1.21
     genius
    1.20
     extraord
    1.20
     Spoiler
    1.18
     temperament
    1.15
     uber
    1.13
     reincarn
    1.13
    Activations Density 0.925%

    No Known Activations