© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43639
    Prev
    Next
    INDEX
    Explanations

    numerical values related to statistics and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    2:0.12
    3:0.06
    4:0.08
    5:0.03
    6:0.36
    7:0.06
    8:0.03
    9:0.05
    10:0.06
    11:0.05
    Negative Logits
    gdala
    -1.39
     rightfully
    -1.37
    iscons
    -1.31
    cients
    -1.30
    ocument
    -1.25
     Leilan
    -1.22
    icians
    -1.21
    ateurs
    -1.17
    LCS
    -1.14
     inaction
    -1.14
    POSITIVE LOGITS
    rc
    1.50
    nova
    1.46
    ogan
    1.38
    iev
    1.34
    bsp
    1.30
    notice
    1.29
    м
    1.29
    ilion
    1.28
    meier
    1.28
    sie
    1.28
    Activations Density 0.060%

    No Known Activations