© 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. 659
    Prev
    Next
    INDEX
    Explanations

    phrases related to apologies and expressions of regret

    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
    1:0.01
    2:0.19
    3:0.18
    4:0.10
    5:0.03
    6:0.07
    7:0.03
    8:0.04
    9:0.07
    10:0.08
    11:0.12
    Negative Logits
    alties
    -1.28
     Gould
    -1.10
     virtues
    -1.08
     adject
    -1.08
    ilial
    -1.06
     suffix
    -1.04
    SPONSORED
    -1.03
    ECD
    -1.03
     Nose
    -1.02
    .—
    -1.02
    POSITIVE LOGITS
    dayName
    1.29
     %%
    1.22
     %
    1.21
    inar
    1.19
    helle
    1.19
    nb
    1.18
    lass
    1.16
    iframe
    1.16
    ouver
    1.14
    vez
    1.13
    Activations Density 0.001%

    No Known Activations