© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43328
    Prev
    Next
    INDEX
    Explanations

    references to committees, commissions, and groups focused on recommendations and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    2:0.06
    3:0.04
    4:0.04
    5:0.05
    6:0.03
    7:0.04
    8:0.03
    9:0.06
    10:0.43
    11:0.13
    Negative Logits
     Brands
    -1.60
     grocer
    -1.42
    wear
    -1.34
     Ft
    -1.33
     percentages
    -1.25
     import
    -1.24
     chic
    -1.23
     Soph
    -1.22
     Lime
    -1.21
     retailer
    -1.21
    POSITIVE LOGITS
     chaired
    2.24
     convened
    2.05
     Chair
    1.89
    sembly
    1.84
     unanimously
    1.83
     presiding
    1.81
     deliberations
    1.79
    member
    1.79
    committee
    1.76
    aye
    1.75
    Activations Density 0.359%

    No Known Activations