© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 42523
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal autonomy and the discussion of choices in moral contexts

    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
    0:0.15
    1:0.19
    2:0.02
    3:0.03
    4:0.02
    5:0.20
    6:0.06
    7:0.01
    8:0.11
    9:0.09
    10:0.02
    11:0.05
    Negative Logits
    cube
    -1.91
    pace
    -1.70
    paces
    -1.69
    iband
    -1.62
    Contin
    -1.61
    contin
    -1.57
     tremend
    -1.53
    flame
    -1.52
    ograp
    -1.48
    omething
    -1.47
    POSITIVE LOGITS
     �
    1.82
    ¯¯
    1.69
     >>
    1.62
     Vald
    1.60
    1.54
     ¯
    1.53
    --------------------------------------------------------
    1.48
      
    1.45
     ―
    1.43
     Wraith
    1.41
    Activations Density 0.011%

    No Known Activations