© 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. 3278
    Prev
    Next
    INDEX
    Explanations

    names of entities, especially those related to bills, series, or specific options within contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.04
    1:0.13
    2:0.03
    3:0.03
    4:0.03
    5:0.42
    6:0.03
    7:0.02
    8:0.05
    9:0.08
    10:0.06
    11:0.03
    Negative Logits
    comed
    -2.31
    ask
    -1.97
    scl
    -1.84
    mp
    -1.82
    accompan
    -1.78
    racial
    -1.74
    hat
    -1.73
    odi
    -1.71
    serv
    -1.71
    gam
    -1.70
    POSITIVE LOGITS
     XVI
    2.05
     XII
    1.97
     XIV
    1.90
     VII
    1.84
     XI
    1.75
     twent
    1.73
     01
    1.69
     Eleven
    1.67
     XIII
    1.65
     XX
    1.64
    Activations Density 0.075%

    No Known Activations