© 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. 5-ATT-KK
    11. 44871
    Prev
    Next
    INDEX
    Explanations

    phrases related to care and treatment for vulnerable individuals, particularly children and animals

    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
    0:0.03
    1:0.02
    2:0.07
    3:0.04
    4:0.10
    5:0.02
    6:0.04
    7:0.38
    8:0.02
    9:0.03
    10:0.12
    11:0.07
    Negative Logits
    moil
    -1.62
     Cosponsors
    -1.56
     datas
    -1.55
    DEM
    -1.44
    govtrack
    -1.43
     sqor
    -1.41
    uably
    -1.40
    zai
    -1.37
    category
    -1.36
    installed
    -1.35
    POSITIVE LOGITS
     grandchildren
    1.82
     safegu
    1.80
    noon
    1.52
     safeguard
    1.48
     daughters
    1.43
     children
    1.36
     Children
    1.35
     sons
    1.35
     trusts
    1.33
     ducks
    1.31
    Activations Density 0.014%

    No Known Activations