© 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. 16759
    Prev
    Next
    INDEX
    Explanations

    negative sentiments toward technology and connectivity issues

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.03
    3:0.05
    4:0.03
    5:0.03
    6:0.35
    7:0.08
    8:0.03
    9:0.04
    10:0.21
    11:0.06
    Negative Logits
     Parables
    -1.56
     Monetary
    -1.54
     sentence
    -1.44
     paragraphs
    -1.40
     Mermaid
    -1.37
     hereditary
    -1.36
    ukemia
    -1.35
     remorse
    -1.33
     verdict
    -1.33
    )=(
    -1.33
    POSITIVE LOGITS
    talk
    1.73
    secure
    1.69
    inki
    1.68
    disabled
    1.58
    enabled
    1.56
    coded
    1.53
    hop
    1.52
    puter
    1.48
    hare
    1.47
    repeat
    1.44
    Activations Density 0.001%

    No Known Activations