© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 41598
    Prev
    Next
    INDEX
    Explanations

    terms related to universal rights and access to services

    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
    1:0.03
    2:0.06
    3:0.04
    4:0.07
    5:0.04
    6:0.29
    7:0.16
    8:0.03
    9:0.04
    10:0.08
    11:0.07
    Negative Logits
    selves
    -1.32
     Mehran
    -1.26
     Papa
    -1.26
     Frey
    -1.17
    apeake
    -1.16
    icho
    -1.15
    scenes
    -1.15
     bro
    -1.14
     Hamb
    -1.13
    omo
    -1.13
    POSITIVE LOGITS
    isSpecialOrderable
    1.51
    RANT
    1.29
     exception
    1.26
    omial
    1.25
    rosso
    1.25
    IQ
    1.23
    ATIONS
    1.22
    rities
    1.22
     Extend
    1.22
     Mean
    1.22
    Activations Density 0.002%

    No Known Activations