© 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. 19229
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to evaluating or assessing strengths and weaknesses

    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
    0:0.04
    1:0.15
    2:0.04
    3:0.04
    4:0.09
    5:0.03
    6:0.05
    7:0.18
    8:0.05
    9:0.05
    10:0.03
    11:0.21
    Negative Logits
     supervision
    -2.36
     slab
    -2.32
     "$:/
    -2.20
     irrad
    -2.18
     debris
    -2.16
    oller
    -2.14
     Mohammad
    -2.12
    displayText
    -2.11
     stret
    -2.10
     supervised
    -2.08
    POSITIVE LOGITS
     weaknesses
    4.25
     strengths
    3.62
     flaws
    3.18
     failings
    2.81
     vulnerabilities
    2.77
     weakness
    2.73
    weak
    2.72
    Trivia
    2.71
     shortcomings
    2.60
    Weak
    2.56
    Activations Density 0.004%

    No Known Activations