© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 38042
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of liability and responsibility

    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
    0:0.02
    1:0.02
    2:0.06
    3:0.08
    4:0.08
    5:0.03
    6:0.04
    7:0.42
    8:0.02
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
    NRS
    -1.58
    �
    -1.54
    Works
    -1.53
    Reply
    -1.51
    rist
    -1.48
     digs
    -1.44
    idelines
    -1.43
    シャ
    -1.41
    atography
    -1.40
    Staff
    -1.38
    POSITIVE LOGITS
     volatility
    1.76
     deterioration
    1.65
     emergence
    1.64
     erosion
    1.61
     relapse
    1.60
     instability
    1.56
     setbacks
    1.50
     Discrimination
    1.45
     looming
    1.45
     inaction
    1.41
    Activations Density 0.001%

    No Known Activations