© 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. 10-ATT-KK
    11. 15138
    Prev
    Next
    INDEX
    Explanations

    themes related to missing persons and their circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.02
    3:0.03
    4:0.03
    5:0.63
    6:0.01
    7:0.02
    8:0.01
    9:0.11
    10:0.01
    11:0.03
    Negative Logits
    OULD
    -2.82
    WAR
    -2.61
    ERE
    -2.57
    ardless
    -2.56
     SEE
    -2.56
     BELOW
    -2.55
     Trayvon
    -2.47
    >]
    -2.44
    CLUS
    -2.42
     IF
    -2.41
    POSITIVE LOGITS
     since
    6.33
     ever
    6.31
    since
    5.82
     lately
    5.43
    ever
    5.16
     forever
    4.51
     EVER
    4.43
    Ever
    4.14
     until
    4.03
     intermitt
    3.96
    Activations Density 0.541%

    No Known Activations