© 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. 8293
    Prev
    Next
    INDEX
    Explanations

    themes related to suffering and the consequences of social and political issues

    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
    0:0.03
    1:0.02
    2:0.05
    3:0.06
    4:0.11
    5:0.38
    6:0.01
    7:0.03
    8:0.02
    9:0.18
    10:0.02
    11:0.03
    Negative Logits
     unfocusedRange
    -2.81
    umbn
    -2.63
    uese
    -2.51
    \)
    -2.40
    kus
    -2.40
    Regarding
    -2.37
    VS
    -2.32
     fixme
    -2.32
     ));
    -2.30
     Topic
    -2.30
    POSITIVE LOGITS
     untold
    4.62
     unimaginable
    4.09
     unthinkable
    3.80
     millennia
    3.73
     doomed
    3.73
     scarcely
    3.69
     anew
    3.68
     unsus
    3.58
     endlessly
    3.58
     forever
    3.57
    Activations Density 1.110%

    No Known Activations