© 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. 10-ATT-KK
    11. 6973
    Prev
    Next
    INDEX
    Explanations

    advice and strategies related to personal safety and self-improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.06
    2:0.07
    3:0.06
    4:0.08
    5:0.19
    6:0.06
    7:0.07
    8:0.05
    9:0.16
    10:0.04
    11:0.05
    Negative Logits
     effected
    -2.82
    �士
    -2.63
    lished
    -2.60
     perished
    -2.60
    ceivable
    -2.56
    tained
    -2.54
     seized
    -2.53
     sided
    -2.50
    alysed
    -2.48
    apsed
    -2.45
    POSITIVE LOGITS
     Your
    3.79
    Your
    3.75
     Explain
    3.72
    Make
    3.62
     Make
    3.56
    imize
    3.43
    cknow
    3.42
     Provide
    3.42
     Include
    3.42
    Remember
    3.31
    Activations Density 0.339%

    No Known Activations