© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15480
    Prev
    Next
    INDEX
    Explanations

    issues surrounding political engagement and obligations

    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
    2:0.04
    3:0.04
    4:0.05
    5:0.49
    6:0.02
    7:0.03
    8:0.03
    9:0.13
    10:0.03
    11:0.03
    Negative Logits
    rather
    -3.34
     rather
    -3.11
     notwithstanding
    -2.79
     instead
    -2.54
     Idle
    -2.43
    mostly
    -2.42
     Mostly
    -2.37
     minus
    -2.35
    ��
    -2.31
     may
    -2.28
    POSITIVE LOGITS
    yet
    4.48
     yet
    4.23
     enough
    3.89
    enough
    3.63
     anymore
    3.56
     soon
    3.30
     immediately
    3.28
    ?",
    3.15
     already
    3.09
    then
    3.02
    Activations Density 0.202%

    No Known Activations