© 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. 9019
    Prev
    Next
    INDEX
    Explanations

    instances of digital communication and associated actions

    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
    1:0.02
    2:0.03
    3:0.04
    4:0.07
    5:0.02
    6:0.06
    7:0.11
    8:0.01
    9:0.07
    10:0.03
    11:0.44
    Negative Logits
    allery
    -2.58
    raint
    -2.27
     criterion
    -2.27
    itect
    -2.09
     myth
    -2.08
     Hist
    -2.07
     horizon
    -2.06
     breadth
    -2.02
     heterogeneity
    -2.00
     aspect
    -1.99
    POSITIVE LOGITS
     emails
    4.79
     messages
    4.79
     Emails
    4.39
     notifications
    4.13
     letters
    4.08
    letters
    4.04
     invitations
    4.00
     email
    3.86
     replies
    3.71
     newsletters
    3.70
    Activations Density 0.489%

    No Known Activations