© 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. 7792
    Prev
    Next
    INDEX
    Explanations

    themes related to conflict, control, and exploitation of individuals or groups

    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
    1:0.01
    2:0.10
    3:0.06
    4:0.11
    5:0.34
    6:0.02
    7:0.03
    8:0.01
    9:0.18
    10:0.02
    11:0.02
    Negative Logits
     didnt
    -3.19
    was
    -3.06
    terday
    -3.00
    "))
    -2.99
     Went
    -2.90
    ould
    -2.90
    �
    -2.85
     �
    -2.83
    @#&
    -2.82
    ?".
    -2.80
    POSITIVE LOGITS
     or
    3.87
     rather
    3.59
    often
    3.51
     preferring
    3.45
     lest
    3.41
     merely
    3.34
     unnecessarily
    3.29
     Often
    3.17
     themselves
    3.15
     simply
    3.15
    Activations Density 1.388%

    No Known Activations