© 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. 44017
    Prev
    Next
    INDEX
    Explanations

    instances of the word "until."

    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
    1:0.02
    2:0.11
    3:0.07
    4:0.14
    5:0.03
    6:0.04
    7:0.11
    8:0.05
    9:0.03
    10:0.12
    11:0.20
    Negative Logits
     Chronic
    -1.34
     Species
    -1.32
    tan
    -1.31
     Yam
    -1.24
     subordinate
    -1.19
     @@
    -1.18
     Kod
    -1.18
    helial
    -1.17
     Clan
    -1.16
     Chin
    -1.15
    POSITIVE LOGITS
    asio
    1.44
    cffff
    1.40
    bnb
    1.40
    apo
    1.39
    Cand
    1.36
     spoof
    1.36
    reader
    1.34
    ournal
    1.32
    livious
    1.31
    Override
    1.29
    Activations Density 0.023%

    No Known Activations