© 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. 2859
    Prev
    Next
    INDEX
    Explanations

    attributes and qualities that describe individuals positively

    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
    0:0.08
    1:0.04
    2:0.11
    3:0.23
    4:0.03
    5:0.11
    6:0.02
    7:0.08
    8:0.04
    9:0.01
    10:0.15
    11:0.02
    Negative Logits
     leaked
    -2.32
    iatus
    -2.15
     Worse
    -2.09
     defaults
    -2.01
    azo
    -2.01
     encro
    -1.96
     Mandatory
    -1.95
    機
    -1.93
     fallout
    -1.91
     fragmentation
    -1.91
    POSITIVE LOGITS
     loved
    3.01
     loving
    3.00
     cheerful
    2.92
     passionate
    2.89
     caring
    2.87
     wonderful
    2.81
     happiest
    2.80
     thoughtful
    2.75
     kindness
    2.68
    cellent
    2.58
    Activations Density 0.323%

    No Known Activations