© 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. 12719
    Prev
    Next
    INDEX
    Explanations

    phrases related to community engagement and advocacy efforts

    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
    0:0.02
    1:0.01
    2:0.02
    3:0.02
    4:0.06
    5:0.17
    6:0.02
    7:0.02
    8:0.01
    9:0.56
    10:0.01
    11:0.03
    Negative Logits
    Adds
    -2.82
    Increases
    -2.77
     Starts
    -2.66
    allows
    -2.56
    reads
    -2.56
    tains
    -2.50
    Allows
    -2.42
    shows
    -2.33
    Impro
    -2.28
    interstitial
    -2.26
    POSITIVE LOGITS
     themselves
    4.86
    their
    4.70
     their
    4.05
     have
    4.00
    Their
    3.90
    have
    3.88
     are
    3.88
     THEIR
    3.84
     aren
    3.79
     were
    3.58
    Activations Density 3.535%

    No Known Activations