© 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. 43707
    Prev
    Next
    INDEX
    Explanations

    statements containing conditional phrases or hypothetical scenarios

    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
    2:0.08
    3:0.37
    4:0.13
    5:0.04
    6:0.03
    7:0.04
    8:0.05
    9:0.05
    10:0.06
    11:0.06
    Negative Logits
    rawdownloadcloneembedreportprint
    -2.12
    omen
    -1.85
    Synopsis
    -1.72
     [...]
    -1.63
    [/
    -1.57
    Analysis
    -1.55
     commons
    -1.55
    ..."
    -1.51
    "],"
    -1.45
    cember
    -1.45
    POSITIVE LOGITS
     Bieber
    1.68
    ozy
    1.67
     Rove
    1.61
     Giuliani
    1.61
     CoC
    1.58
     steroids
    1.51
     downright
    1.51
     pesky
    1.50
    ucket
    1.50
     iPads
    1.49
    Activations Density 0.003%

    No Known Activations