© 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. 43717
    Prev
    Next
    INDEX
    Explanations

    occurrences of verbs or phrases indicating future intentions or confirmations

    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
    2:0.10
    3:0.13
    4:0.13
    5:0.02
    6:0.20
    7:0.15
    8:0.03
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
    instead
    -1.44
     instead
    -1.38
     Wouldn
    -1.35
    izontal
    -1.31
    rather
    -1.29
     simplicity
    -1.27
     sake
    -1.22
    ordinary
    -1.21
    icons
    -1.19
     rather
    -1.19
    POSITIVE LOGITS
    yet
    2.03
     satisf
    1.69
     yet
    1.65
     confir
    1.62
     nor
    1.51
     acknow
    1.47
     officially
    1.44
     agre
    1.40
     laun
    1.40
     formally
    1.39
    Activations Density 0.006%

    No Known Activations