© 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. 44123
    Prev
    Next
    INDEX
    Explanations

    references to people and their interactions in various contexts

    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
    1:0.01
    2:0.07
    3:0.10
    4:0.17
    5:0.02
    6:0.07
    7:0.22
    8:0.05
    9:0.03
    10:0.06
    11:0.13
    Negative Logits
    displayText
    -1.68
    ONSORED
    -1.63
    Hours
    -1.62
    龍喚士
    -1.46
     Morty
    -1.45
    FontSize
    -1.42
     Hours
    -1.42
     Heist
    -1.41
    DEBUG
    -1.38
    EMBER
    -1.35
    POSITIVE LOGITS
     regress
    1.74
    lict
    1.56
    rises
    1.50
    unda
    1.44
    develop
    1.44
    development
    1.44
    lik
    1.40
    forth
    1.39
     plaintiffs
    1.37
     plaintiff
    1.35
    Activations Density 0.005%

    No Known Activations