© 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. 46335
    Prev
    Next
    INDEX
    Explanations

    phrases indicating moral judgement or criticism of behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.12
    1:0.21
    2:0.03
    3:0.04
    4:0.05
    5:0.15
    6:0.13
    7:0.01
    8:0.05
    9:0.09
    10:0.04
    11:0.03
    Negative Logits
    IDENT
    -1.75
    interstitial
    -1.69
    restrial
    -1.61
    ISC
    -1.61
    76561
    -1.56
    digit
    -1.53
    trip
    -1.50
    �
    -1.49
    plet
    -1.47
    NP
    -1.44
    POSITIVE LOGITS
     Conclusion
    1.70
     Gothic
    1.64
    �
    1.59
     Mods
    1.58
     Signs
    1.56
     furthermore
    1.51
     Brus
    1.50
     Again
    1.48
     Goodman
    1.46
     endif
    1.45
    Activations Density 0.021%

    No Known Activations