© 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. 43924
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal language and its implications

    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
    2:0.07
    3:0.04
    4:0.11
    5:0.03
    6:0.03
    7:0.35
    8:0.02
    9:0.03
    10:0.13
    11:0.08
    Negative Logits
    gins
    -1.50
    Legendary
    -1.41
     pilgr
    -1.40
    etheus
    -1.40
    earchers
    -1.39
    runs
    -1.38
    76561
    -1.38
     telescopes
    -1.36
     astronomer
    -1.32
     journeys
    -1.32
    POSITIVE LOGITS
     TEXT
    1.73
    paragraph
    1.73
    enum
    1.51
    anguage
    1.46
    TEXT
    1.46
    appro
    1.46
    『
    1.45
     paragraphs
    1.43
    Struct
    1.43
     CoC
    1.43
    Activations Density 0.013%

    No Known Activations