© 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. 9-ATT-KK
    11. 17420
    Prev
    Next
    INDEX
    Explanations

    phrases that foster positive experiences and support personal well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.02
    2:0.06
    3:0.14
    4:0.02
    5:0.05
    6:0.01
    7:0.05
    8:0.02
    9:0.01
    10:0.45
    11:0.01
    Negative Logits
     juven
    -2.05
     lob
    -2.01
     staged
    -1.90
     purported
    -1.89
     pont
    -1.78
     combination
    -1.77
     accumulated
    -1.76
    recent
    -1.75
     stockp
    -1.75
     gestation
    -1.74
    POSITIVE LOGITS
     easier
    3.60
     safer
    3.23
     smoother
    2.91
     clearer
    2.90
     healthier
    2.73
     harder
    2.70
     stronger
    2.69
     happier
    2.66
     better
    2.66
     quicker
    2.65
    Activations Density 0.340%

    No Known Activations