© 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. 19410
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of concern related to social issues and community dynamics

    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
    0:0.10
    1:0.02
    2:0.14
    3:0.10
    4:0.30
    5:0.10
    6:0.02
    7:0.04
    8:0.02
    9:0.05
    10:0.02
    11:0.02
    Negative Logits
    "),
    -2.46
     "
    -2.36
    owship
    -2.36
     humorous
    -2.35
     "<
    -2.30
    roma
    -2.25
     Squirrel
    -2.21
    "))
    -2.20
    elvet
    -2.19
     Surprise
    -2.19
    POSITIVE LOGITS
    .」
    5.39
    .�
    4.78
     �
    4.61
    �
    4.54
    .''
    4.45
    ‑
    4.40
    」
    4.11
     ►
    4.03
    ?」
    3.67
    ''.
    3.67
    Activations Density 0.785%

    No Known Activations