© 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. 46226
    Prev
    Next
    INDEX
    Explanations

    phrases that express empowerment and activism

    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
    2:0.42
    3:0.11
    4:0.08
    5:0.03
    6:0.05
    7:0.04
    8:0.05
    9:0.02
    10:0.07
    11:0.05
    Negative Logits
     Meaning
    -1.60
     Signature
    -1.60
     Leaves
    -1.47
     Schwar
    -1.45
     Shak
    -1.44
     RU
    -1.39
     Stability
    -1.36
     Juven
    -1.35
     Slash
    -1.34
     ransom
    -1.34
    POSITIVE LOGITS
    agree
    1.94
    uckland
    1.77
    imore
    1.75
     constitute
    1.69
    phrine
    1.65
     conceive
    1.64
    poke
    1.62
    ividual
    1.62
     deserve
    1.61
    incinn
    1.57
    Activations Density 0.050%

    No Known Activations