© 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. 7128
    Prev
    Next
    INDEX
    Explanations

    entities and interactions related to online or digital environments

    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
    1:0.08
    2:0.06
    3:0.06
    4:0.05
    5:0.04
    6:0.03
    7:0.07
    8:0.41
    9:0.05
    10:0.04
    11:0.04
    Negative Logits
    escription
    -2.67
    =]
    -2.19
    olars
    -2.13
    geoning
    -2.08
     outnumbered
    -2.06
    ynchronous
    -2.02
    vae
    -1.90
    rament
    -1.87
    uper
    -1.85
    aspers
    -1.82
    POSITIVE LOGITS
    which
    5.06
     which
    4.94
    that
    4.63
    who
    4.61
     who
    4.54
     Which
    4.49
    Which
    4.46
     whom
    4.24
     whose
    4.24
    where
    4.23
    Activations Density 0.171%

    No Known Activations