© 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. 9-ATT-KK
    11. 18434
    Prev
    Next
    INDEX
    Explanations

    references to formal titles and positions in an organizational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.03
    2:0.03
    3:0.57
    4:0.01
    5:0.05
    6:0.02
    7:0.03
    8:0.03
    9:0.02
    10:0.08
    11:0.01
    Negative Logits
     realism
    -2.24
     nostalgia
    -2.10
     inconvenience
    -2.01
     sentiment
    -1.95
    expression
    -1.94
     nationalism
    -1.92
    population
    -1.91
    ismo
    -1.90
    icism
    -1.88
    atism
    -1.88
    POSITIVE LOGITS
     secretaries
    2.98
     Cups
    2.89
     pairs
    2.82
     sisters
    2.69
     columns
    2.65
     mentors
    2.63
     towers
    2.62
     slots
    2.62
     finalists
    2.62
     pillars
    2.56
    Activations Density 0.560%

    No Known Activations