© 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. 47221
    Prev
    Next
    INDEX
    Explanations

    terms related to internet regulations and net neutrality

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.06
    3:0.08
    4:0.05
    5:0.06
    6:0.03
    7:0.04
    8:0.05
    9:0.13
    10:0.29
    11:0.10
    Negative Logits
     [+
    -1.59
    Appearance
    -1.57
     Healer
    -1.51
     hypnot
    -1.47
    Inv
    -1.44
     Alchemist
    -1.42
     Venom
    -1.42
     charms
    -1.40
    Ingredients
    -1.39
    spell
    -1.36
    POSITIVE LOGITS
     dissenting
    1.71
     protections
    1.68
     dissent
    1.60
     safeguards
    1.59
     divest
    1.55
    levard
    1.52
    untled
    1.50
     conservatives
    1.50
     Amendments
    1.49
     compromise
    1.47
    Activations Density 0.009%

    No Known Activations