© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 41720
    Prev
    Next
    INDEX
    Explanations

    references to anti-groups or organizations

    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
    0:0.08
    1:0.16
    2:0.04
    3:0.04
    4:0.02
    5:0.15
    6:0.12
    7:0.08
    8:0.03
    9:0.05
    10:0.08
    11:0.08
    Negative Logits
     0004
    -1.42
     sled
    -1.39
     Tee
    -1.32
     previews
    -1.30
     holster
    -1.30
     Sieg
    -1.26
     preview
    -1.25
     Username
    -1.23
     pasture
    -1.21
     scratches
    -1.21
    POSITIVE LOGITS
    stress
    1.64
    hibition
    1.62
    drug
    1.61
    cycl
    1.54
    peak
    1.52
    complex
    1.52
    zee
    1.52
    mining
    1.52
    business
    1.50
    ruption
    1.50
    Activations Density 0.003%

    No Known Activations