© 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. 42916
    Prev
    Next
    INDEX
    Explanations

    phrases associated with the concept of "business" within 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
    1:0.02
    2:0.13
    3:0.04
    4:0.15
    5:0.04
    6:0.03
    7:0.24
    8:0.03
    9:0.05
    10:0.08
    11:0.09
    Negative Logits
    tsy
    -1.33
     canceled
    -1.31
     looming
    -1.26
     extinguished
    -1.26
     levied
    -1.25
    ancel
    -1.22
     Bunker
    -1.21
     arrived
    -1.20
     nearby
    -1.19
     lost
    -1.19
    POSITIVE LOGITS
     psychiat
    1.53
    DATA
    1.45
     rendition
    1.42
     Palestin
    1.35
     confir
    1.34
    ocide
    1.31
     anonymity
    1.28
     conceal
    1.28
    texture
    1.26
    DES
    1.26
    Activations Density 0.000%

    No Known Activations