© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 42390
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "without further ado."

    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
    0:0.01
    1:0.01
    2:0.09
    3:0.18
    4:0.24
    5:0.02
    6:0.02
    7:0.18
    8:0.05
    9:0.04
    10:0.05
    11:0.05
    Negative Logits
    prus
    -1.91
    ento
    -1.52
    elled
    -1.50
    ortium
    -1.48
    ptives
    -1.46
    ovo
    -1.46
    rimp
    -1.45
    ricane
    -1.45
    ndra
    -1.45
    ricanes
    -1.43
    POSITIVE LOGITS
    �
    1.63
    Topics
    1.61
     goodness
    1.54
     corrid
    1.49
    Discussion
    1.48
     mah
    1.48
    Chapter
    1.46
     adventure
    1.43
     delightful
    1.42
     Goodbye
    1.42
    Activations Density 0.001%

    No Known Activations