© 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. 21773
    Prev
    Next
    INDEX
    Explanations

    key elements related to societal issues and political events

    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
    2:0.03
    3:0.04
    4:0.13
    5:0.51
    6:0.02
    7:0.05
    8:0.02
    9:0.07
    10:0.02
    11:0.02
    Negative Logits
    .:
    -3.23
    pecially
    -3.17
    !:
    -3.02
    but
    -2.99
     =>
    -2.98
     Except
    -2.97
    Except
    -2.94
     BUT
    -2.83
     THEN
    -2.73
    ':
    -2.71
    POSITIVE LOGITS
     remains
    6.44
     still
    5.70
     persists
    5.49
     nonetheless
    5.38
     continues
    4.97
     nevertheless
    4.96
     retains
    4.65
    still
    4.61
     remain
    4.59
     hasn
    4.36
    Activations Density 1.419%

    No Known Activations