© 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. 3-ATT-KK
    11. 8138
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or expressions indicating uncertainty or alternative scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.06
    2:0.06
    3:0.04
    4:0.02
    5:0.08
    6:0.05
    7:0.04
    8:0.07
    9:0.33
    10:0.08
    11:0.08
    Negative Logits
    onia
    -1.40
    andering
    -1.23
     Ale
    -1.18
    onne
    -1.17
     Byron
    -1.16
     Birthday
    -1.16
    icultural
    -1.15
    ogie
    -1.15
    ito
    -1.12
    ir
    -1.12
    POSITIVE LOGITS
    etheless
    1.80
     agre
    1.61
     scrut
    1.51
    ...?
    1.44
    ?????
    1.33
    emort
    1.33
     certs
    1.30
    ItemTracker
    1.26
     confir
    1.26
     timeframe
    1.25
    Activations Density 0.009%

    No Known Activations