© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 35197
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases that indicate relationships or dependencies

    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
    0:0.02
    1:0.01
    2:0.13
    3:0.07
    4:0.11
    5:0.02
    6:0.04
    7:0.26
    8:0.05
    9:0.03
    10:0.12
    11:0.08
    Negative Logits
     overload
    -1.58
    igon
    -1.54
    variable
    -1.50
     Radio
    -1.49
    music
    -1.47
    Flow
    -1.46
    nel
    -1.46
     Symphony
    -1.45
     Hamburg
    -1.44
    lance
    -1.42
    POSITIVE LOGITS
     pedest
    2.28
     merits
    1.96
    isSpecialOrderable
    1.84
     Supporting
    1.77
     Tradable
    1.76
     unworthy
    1.75
     accol
    1.70
     merit
    1.69
    龍契士
    1.68
    Claim
    1.64
    Activations Density 0.000%

    No Known Activations