© 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. 39466
    Prev
    Next
    INDEX
    Explanations

    points and guidelines relating to safety and caution

    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
    0:0.17
    1:0.08
    2:0.04
    3:0.04
    4:0.04
    5:0.20
    6:0.07
    7:0.01
    8:0.10
    9:0.08
    10:0.06
    11:0.05
    Negative Logits
     scrimmage
    -1.80
     █
    -1.71
     psy
    -1.68
     paddle
    -1.62
     f
    -1.62
     AX
    -1.54
     overdose
    -1.52
     stigma
    -1.52
     troll
    -1.51
     seiz
    -1.51
    POSITIVE LOGITS
    Compan
    2.61
    Document
    2.48
    Contin
    2.46
    Installation
    2.46
    Des
    2.42
    Requ
    2.42
    Sir
    2.40
    Custom
    2.40
    Premium
    2.40
    Need
    2.39
    Activations Density 0.004%

    No Known Activations