© 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. 20194
    Prev
    Next
    INDEX
    Explanations

    structured information and organizational details relating to events or statistics

    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
    0:0.03
    1:0.35
    2:0.05
    3:0.04
    4:0.04
    5:0.04
    6:0.14
    7:0.03
    8:0.02
    9:0.13
    10:0.03
    11:0.05
    Negative Logits
     dangling
    -2.92
    inders
    -2.82
    paying
    -2.81
    EStreamFrame
    -2.73
     tether
    -2.69
    things
    -2.58
     compan
    -2.58
    hesive
    -2.52
    �
    -2.48
     manufactures
    -2.46
    POSITIVE LOGITS
     79
    7.31
     78
    7.10
     69
    7.09
     77
    7.03
     71
    6.97
     83
    6.86
     68
    6.79
     67
    6.78
     63
    6.78
     81
    6.72
    Activations Density 0.076%

    No Known Activations