© 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. 43476
    Prev
    Next
    INDEX
    Explanations

    version numbers and updates in software-related contexts

    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
    2:0.09
    3:0.05
    4:0.05
    5:0.03
    6:0.19
    7:0.15
    8:0.04
    9:0.05
    10:0.18
    11:0.08
    Negative Logits
     bets
    -1.58
    iture
    -1.47
     aisle
    -1.44
    urities
    -1.42
    iator
    -1.41
    elight
    -1.41
    uable
    -1.36
    ourcing
    -1.35
    ounding
    -1.34
    itures
    -1.32
    POSITIVE LOGITS
    Released
    1.61
    spir
    1.56
    emort
    1.47
    dated
    1.45
    beta
    1.44
    catentry
    1.39
    brew
    1.38
     Released
    1.35
    incarn
    1.34
    Beta
    1.34
    Activations Density 0.003%

    No Known Activations