© 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. 34293
    Prev
    Next
    INDEX
    Explanations

    statements that assert the concept of "truth" and its negation

    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
    1:0.02
    2:0.14
    3:0.11
    4:0.17
    5:0.03
    6:0.10
    7:0.18
    8:0.03
    9:0.03
    10:0.06
    11:0.06
    Negative Logits
     haircut
    -1.60
    ˈ
    -1.34
     shorth
    -1.33
    ヘ
    -1.27
     nickname
    -1.26
     replaces
    -1.24
     crossover
    -1.23
     tabletop
    -1.22
     periodic
    -1.21
     survivor
    -1.21
    POSITIVE LOGITS
     anymore
    1.51
    cms
    1.51
    ilipp
    1.45
    iasm
    1.42
    aim
    1.40
    PLIED
    1.37
     nor
    1.32
    illard
    1.31
    rea
    1.31
     Gou
    1.28
    Activations Density 0.001%

    No Known Activations