© 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. 729
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating ranges or processes

    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
    0:0.02
    1:0.24
    2:0.03
    3:0.10
    4:0.03
    5:0.31
    6:0.03
    7:0.05
    8:0.03
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
     Difference
    -2.54
    ocaust
    -2.50
    gaard
    -2.49
     froze
    -2.44
     Percentage
    -2.43
     Genocide
    -2.40
     MMR
    -2.36
    azo
    -2.34
     dioxide
    -2.25
    inyl
    -2.25
    POSITIVE LOGITS
     doubtless
    2.82
    phasis
    2.75
     sugg
    2.64
    PLA
    2.52
    initely
    2.49
     evidently
    2.49
     emphatically
    2.49
     kindred
    2.48
    displayText
    2.48
     reiterate
    2.46
    Activations Density 0.005%

    No Known Activations