© 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. 2-ATT-KK
    11. 21339
    Prev
    Next
    INDEX
    Explanations

    words related to escape, usually involving challenging or dangerous situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.04
    2:0.15
    3:0.06
    4:0.04
    5:0.09
    6:0.02
    7:0.03
    8:0.18
    9:0.15
    10:0.07
    11:0.03
    Negative Logits
    soDeliveryDate
    -1.53
     Tradable
    -1.09
    Created
    -1.09
    nergy
    -1.08
     Voting
    -1.08
     Implementation
    -1.08
    manship
    -1.08
    NFL
    -1.08
     Barber
    -1.07
     Opinion
    -1.04
    POSITIVE LOGITS
     fumes
    1.55
     boredom
    1.25
     bloodstream
    1.23
    lys
    1.19
     poisoning
    1.17
     pneumonia
    1.16
     flames
    1.15
     parachute
    1.15
     contam
    1.15
     loneliness
    1.15
    Activations Density 0.020%

    No Known Activations