© 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. 42895
    Prev
    Next
    INDEX
    Explanations

    phrases indicating familial relationships and the number of family members

    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
    1:0.02
    2:0.10
    3:0.04
    4:0.05
    5:0.02
    6:0.33
    7:0.07
    8:0.04
    9:0.03
    10:0.12
    11:0.11
    Negative Logits
    worldly
    -1.61
    yip
    -1.55
    untarily
    -1.36
    inarily
    -1.30
    anced
    -1.25
    psc
    -1.24
    venient
    -1.23
    earable
    -1.22
    aturally
    -1.21
    opathic
    -1.20
    POSITIVE LOGITS
     Marshall
    1.29
     Dinner
    1.13
     Sierra
    1.12
     Ashley
    1.11
     collaborator
    1.09
     Valerie
    1.09
     Bind
    1.09
    Gaza
    1.08
     Sue
    1.08
    Deb
    1.07
    Activations Density 0.030%

    No Known Activations