© 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. 10-ATT-KK
    6. 15048
    Prev
    Next
    INDEX
    Explanations

    references to saving or rescuing entities, particularly in contexts that involve life-threatening situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.03
    3:0.05
    4:0.06
    5:0.09
    6:0.03
    7:0.05
    8:0.01
    9:0.18
    10:0.02
    11:0.37
    Negative Logits
    venants
    -2.23
    EMENT
    -2.14
    foreseen
    -2.09
     negativity
    -2.07
    guided
    -2.00
    rosso
    -2.00
    κ
    -1.96
    atisf
    -1.95
    joining
    -1.86
     Noise
    -1.85
    POSITIVE LOGITS
     lives
    3.37
     saved
    2.74
     penn
    2.67
     savings
    2.60
    =#
    2.59
     Lives
    2.58
     corpses
    2.42
     dollars
    2.41
    inea
    2.40
     saving
    2.23
    Activations Density 0.018%

    No Known Activations