© 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. 5-ATT-KK
    6. 42755
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to absence or ongoing struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.25
    3:0.09
    4:0.21
    5:0.02
    6:0.05
    7:0.08
    8:0.04
    9:0.03
    10:0.08
    11:0.06
    Negative Logits
    soDeliveryDate
    -1.91
    minecraft
    -1.70
     srfAttach
    -1.68
    soType
    -1.67
     pecul
    -1.54
    eret
    -1.53
    olars
    -1.52
    deck
    -1.51
     decks
    -1.51
    olar
    -1.50
    POSITIVE LOGITS
     prematurely
    2.60
     altogether
    2.04
     rash
    1.95
    bery
    1.88
     reliance
    1.87
     unnecessarily
    1.69
     deaths
    1.67
     Quit
    1.63
     captivity
    1.61
     needless
    1.59
    Activations Density 0.030%

    No Known Activations