© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 44109
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the construction or development of something from an initial state

    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
    2:0.17
    3:0.07
    4:0.20
    5:0.03
    6:0.09
    7:0.11
    8:0.06
    9:0.04
    10:0.09
    11:0.06
    Negative Logits
     disapproval
    -1.63
    SPONSORED
    -1.52
     Uri
    -1.48
     Ips
    -1.38
     Bills
    -1.38
     dispute
    -1.38
     Hurricanes
    -1.35
     Sirius
    -1.34
     Nanto
    -1.34
     Cth
    -1.32
    POSITIVE LOGITS
    Reloaded
    1.94
    ythm
    1.83
     cheaply
    1.80
    ntil
    1.74
    FORE
    1.63
    matically
    1.62
     hinges
    1.61
     customized
    1.60
     executes
    1.57
    ADRA
    1.57
    Activations Density 0.001%

    No Known Activations