© 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. 44092
    Prev
    Next
    INDEX
    Explanations

    numbers associated with ages or counts of people involved in incidents

    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
    0:0.08
    1:0.01
    2:0.14
    3:0.06
    4:0.10
    5:0.02
    6:0.08
    7:0.08
    8:0.11
    9:0.03
    10:0.11
    11:0.13
    Negative Logits
    BOOK
    -1.67
    Fail
    -1.64
    ORY
    -1.64
    itism
    -1.48
    Program
    -1.47
    itative
    -1.46
    Book
    -1.42
    UCT
    -1.41
    Rule
    -1.38
    Commercial
    -1.38
    POSITIVE LOGITS
    dinand
    1.95
     Nanto
    1.44
     Hels
    1.43
     Elise
    1.42
     respectively
    1.33
     Reyn
    1.33
     Mb
    1.33
    atel
    1.32
     Lauder
    1.31
     Seym
    1.30
    Activations Density 0.002%

    No Known Activations