© 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. 9-ATT-KK
    11. 413
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "the right place at the right time."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.39
    2:0.05
    3:0.07
    4:0.04
    5:0.06
    6:0.06
    7:0.04
    8:0.02
    9:0.07
    10:0.05
    11:0.04
    Negative Logits
    cellaneous
    -2.82
    iscovered
    -2.65
    ached
    -2.58
     Occasionally
    -2.52
    verages
    -2.47
     Another
    -2.37
    enda
    -2.36
    ences
    -2.36
    stories
    -2.33
    feature
    -2.29
    POSITIVE LOGITS
     right
    4.70
     correct
    4.45
     proper
    4.42
     wrong
    4.40
    right
    3.85
     Right
    3.77
     RIGHT
    3.76
     rightful
    3.61
    wrong
    3.59
    Right
    3.51
    Activations Density 0.027%

    No Known Activations