© 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. 43595
    Prev
    Next
    INDEX
    Explanations

    critical perspectives on social and political issues

    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
    0:0.02
    1:0.01
    2:0.16
    3:0.12
    4:0.14
    5:0.02
    6:0.02
    7:0.13
    8:0.04
    9:0.05
    10:0.13
    11:0.09
    Negative Logits
     unloaded
    -1.45
    achev
    -1.33
    abus
    -1.29
     hump
    -1.28
    arted
    -1.23
     destiny
    -1.23
    hillary
    -1.22
    root
    -1.19
    iem
    -1.19
    0000000000000000
    -1.18
    POSITIVE LOGITS
     nowadays
    1.73
    姫
    1.67
    adays
    1.45
     orn
    1.43
     Occupations
    1.34
    cially
    1.32
    since
    1.31
    ORPG
    1.28
    Uncommon
    1.27
    sers
    1.27
    Activations Density 0.193%

    No Known Activations