© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 40569
    Prev
    Next
    INDEX
    Explanations

    references to controlled substances and their classifications

    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
    1:0.01
    2:0.08
    3:0.04
    4:0.05
    5:0.04
    6:0.10
    7:0.16
    8:0.05
    9:0.05
    10:0.27
    11:0.09
    Negative Logits
    Jenn
    -1.55
     Tears
    -1.54
     Grimes
    -1.48
    erest
    -1.48
     Lessons
    -1.42
     healed
    -1.39
     Cros
    -1.39
    ayne
    -1.38
     Insight
    -1.37
     Clair
    -1.37
    POSITIVE LOGITS
    classified
    1.80
     designation
    1.70
     classification
    1.69
    specified
    1.67
     Classification
    1.65
    category
    1.64
     lists
    1.62
    notations
    1.61
     reserved
    1.56
     Schedule
    1.55
    Activations Density 0.001%

    No Known Activations