© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 19317
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to photography and visual documentation

    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
    0:0.10
    1:0.02
    2:0.07
    3:0.14
    4:0.04
    5:0.34
    6:0.02
    7:0.05
    8:0.05
    9:0.03
    10:0.07
    11:0.03
    Negative Logits
     Editing
    -3.22
     editing
    -2.99
     upload
    -2.75
    ��
    -2.67
    CV
    -2.57
     optimized
    -2.56
     uploading
    -2.54
    uploads
    -2.51
    upload
    -2.48
    ensor
    -2.47
    POSITIVE LOGITS
     churches
    3.15
     crumbling
    2.85
     towns
    2.71
     societal
    2.71
     neigh
    2.69
     decaying
    2.69
     blight
    2.64
     motorists
    2.64
    NetMessage
    2.64
     neighborhoods
    2.63
    Activations Density 0.104%

    No Known Activations