© 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. 9234
    Prev
    Next
    INDEX
    Explanations

    elements related to technical specifications and instructions

    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
    1:0.03
    2:0.05
    3:0.05
    4:0.07
    5:0.39
    6:0.03
    7:0.05
    8:0.03
    9:0.15
    10:0.02
    11:0.06
    Negative Logits
    could
    -3.85
     could
    -3.38
    might
    -3.34
     indefinitely
    -3.26
    would
    -3.22
    SPONSORED
    -3.04
     risked
    -3.00
     whim
    -2.99
     might
    -2.98
     Would
    -2.98
    POSITIVE LOGITS
    before
    2.81
    ™:
    2.77
     before
    2.73
     haven
    2.67
    iqu
    2.66
     prior
    2.59
     beforehand
    2.56
     hasn
    2.53
    Plug
    2.47
    actly
    2.46
    Activations Density 0.040%

    No Known Activations