© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6938
    Prev
    Next
    INDEX
    Explanations

    references to characters in historical and literary contexts, particularly related to Jewish identity and the Holocaust

    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
    2:0.04
    3:0.08
    4:0.03
    5:0.18
    6:0.02
    7:0.02
    8:0.09
    9:0.21
    10:0.14
    11:0.07
    Negative Logits
    gencies
    -0.99
    jriwal
    -0.97
    ongyang
    -0.95
     unfolding
    -0.94
    BIP
    -0.92
    jury
    -0.90
    afety
    -0.90
    BLIC
    -0.90
    ENTION
    -0.89
    irens
    -0.89
    POSITIVE LOGITS
     himself
    0.99
     immortal
    0.94
     despised
    0.93
     Anyway
    0.93
     legend
    0.91
     Reply
    0.91
    ".[
    0.91
     ".
    0.89
    ...]
    0.89
    ).[
    0.89
    Activations Density 1.577%

    No Known Activations