© 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. 19735
    Prev
    Next
    INDEX
    Explanations

    references to family and community relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.07
    3:0.06
    4:0.11
    5:0.02
    6:0.03
    7:0.39
    8:0.04
    9:0.03
    10:0.08
    11:0.09
    Negative Logits
    pei
    -1.61
    idine
    -1.59
    ello
    -1.53
    pez
    -1.48
     hiatus
    -1.47
    ucket
    -1.45
    endez
    -1.39
    inav
    -1.36
     patronage
    -1.31
    knife
    -1.31
    POSITIVE LOGITS
    rawdownloadcloneembedreportprint
    1.72
    learn
    1.68
     basics
    1.67
     fundamentals
    1.64
    heit
    1.64
    aution
    1.62
     pertinent
    1.59
     relevant
    1.53
     educate
    1.52
    emies
    1.52
    Activations Density 0.008%

    No Known Activations