© 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. 44795
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and perspectives

    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
    2:0.02
    3:0.03
    4:0.03
    5:0.17
    6:0.01
    7:0.02
    8:0.14
    9:0.11
    10:0.18
    11:0.20
    Negative Logits
    holes
    -1.38
    inyl
    -1.28
     Lobby
    -1.28
    chlor
    -1.24
    embed
    -1.23
    ayers
    -1.22
    clinton
    -1.22
    redients
    -1.21
     Pandora
    -1.21
    ileaks
    -1.17
    POSITIVE LOGITS
    arta
    1.26
     disciplined
    1.23
     sacked
    1.19
     quar
    1.15
     respir
    1.15
     sprint
    1.12
     halluc
    1.10
     grit
    1.09
     retention
    1.08
     Franks
    1.08
    Activations Density 0.452%

    No Known Activations