© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 2097
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to energy, water supply, and other resources

    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
    0:0.04
    1:0.02
    2:0.06
    3:0.24
    4:0.02
    5:0.09
    6:0.02
    7:0.04
    8:0.02
    9:0.01
    10:0.36
    11:0.02
    Negative Logits
    higher
    -1.90
    outed
    -1.75
     optimizations
    -1.72
     pitfalls
    -1.71
    soType
    -1.69
     surprises
    -1.64
    backed
    -1.63
    behind
    -1.62
    iths
    -1.60
     misconceptions
    -1.60
    POSITIVE LOGITS
     entire
    2.19
    illion
    2.18
     suffice
    2.14
     sixty
    2.12
     dozen
    2.12
     TOTAL
    2.12
     forty
    2.07
     thirty
    1.98
     span
    1.97
    ousand
    1.97
    Activations Density 0.631%

    No Known Activations