© 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. 1974
    Prev
    Next
    INDEX
    Explanations

    patterns related to quantities and specific entities within a context, especially concerning legal and medical situations

    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
    0:0.12
    1:0.26
    2:0.03
    3:0.05
    4:0.05
    5:0.14
    6:0.04
    7:0.02
    8:0.07
    9:0.07
    10:0.04
    11:0.04
    Negative Logits
    ENSE
    -1.74
    iko
    -1.73
    ce
    -1.71
    entious
    -1.68
    RAG
    -1.65
    isdom
    -1.62
     Gutenberg
    -1.60
    izers
    -1.59
    ICK
    -1.58
    yss
    -1.57
    POSITIVE LOGITS
     case
    2.27
    case
    2.21
     Case
    2.16
     referral
    1.97
    Case
    1.86
     CASE
    1.85
     complaint
    1.79
     Cases
    1.73
     cases
    1.71
     illustration
    1.67
    Activations Density 0.002%

    No Known Activations