© 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. 26535
    Prev
    Next
    INDEX
    Explanations

    references to significant individuals and their controversial actions or reputations in society

    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
    1:0.01
    2:0.17
    3:0.11
    4:0.25
    5:0.04
    6:0.07
    7:0.07
    8:0.03
    9:0.05
    10:0.05
    11:0.05
    Negative Logits
    ipedia
    -1.67
    ���
    -1.55
    neutral
    -1.46
    ertodd
    -1.44
     nowhere
    -1.38
    loo
    -1.38
    emort
    -1.38
     Prepar
    -1.37
    uin
    -1.36
    osponsors
    -1.35
    POSITIVE LOGITS
    eness
    1.76
     subt
    1.47
    ATIVE
    1.47
     understatement
    1.40
    ilda
    1.38
     departures
    1.35
     distortions
    1.31
    DX
    1.30
    Narr
    1.29
     criticisms
    1.28
    Activations Density 0.006%

    No Known Activations