© 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. 35941
    Prev
    Next
    INDEX
    Explanations

    data related to financial losses or migration statistics

    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
    0:0.04
    1:0.02
    2:0.07
    3:0.10
    4:0.05
    5:0.07
    6:0.02
    7:0.02
    8:0.06
    9:0.17
    10:0.22
    11:0.10
    Negative Logits
    Dialogue
    -1.42
     pier
    -1.35
    intent
    -1.28
     tresp
    -1.26
     vend
    -1.22
    owder
    -1.21
     sabot
    -1.21
     :(
    -1.17
    oldemort
    -1.16
    iverpool
    -1.16
    POSITIVE LOGITS
    Average
    1.96
     Statistics
    1.88
     averages
    1.74
     Average
    1.66
     estimates
    1.63
     forecasts
    1.63
     benchmark
    1.63
     statistic
    1.58
     Trends
    1.56
     OECD
    1.54
    Activations Density 1.068%

    No Known Activations