© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 519
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of absurdity or strangeness

    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
    0:0.08
    1:0.17
    2:0.10
    3:0.06
    4:0.02
    5:0.03
    6:0.17
    7:0.04
    8:0.02
    9:0.21
    10:0.03
    11:0.02
    Negative Logits
    NetMessage
    -3.47
    inventoryQuantity
    -3.19
     Wallet
    -3.01
    cel
    -2.97
     ›
    -2.95
     Sins
    -2.87
    PsyNetMessage
    -2.87
     Gib
    -2.86
    gra
    -2.78
    "]=>
    -2.76
    POSITIVE LOGITS
     bizarre
    5.03
     weird
    4.97
     strange
    4.88
     anomal
    4.62
     Weird
    4.60
     strang
    4.51
     crazy
    4.48
     odd
    4.46
     Strange
    4.37
     surreal
    4.34
    Activations Density 0.020%

    No Known Activations