© 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. 5-ATT-KK
    11. 20042
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details about computer hardware components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.04
    1:0.02
    2:0.09
    3:0.07
    4:0.06
    5:0.10
    6:0.02
    7:0.03
    8:0.09
    9:0.10
    10:0.17
    11:0.16
    Negative Logits
    hower
    -0.94
     handcuffs
    -0.93
    ocrates
    -0.92
    jri
    -0.92
     scaff
    -0.91
    inders
    -0.88
    opped
    -0.85
    fac
    -0.82
    past
    -0.80
     appellant
    -0.80
    POSITIVE LOGITS
     guiName
    1.13
     optionally
    1.03
     Vulkan
    0.99
     crossover
    0.99
    taboola
    0.98
     overcl
    0.95
     DX
    0.94
     SLI
    0.92
     Variant
    0.92
     RGB
    0.92
    Activations Density 0.450%

    No Known Activations