© 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. 7687
    Prev
    Next
    INDEX
    Explanations

    references to communication and interaction among people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.14
    3:0.18
    4:0.24
    5:0.02
    6:0.03
    7:0.11
    8:0.04
    9:0.03
    10:0.07
    11:0.05
    Negative Logits
    ipel
    -1.68
    izoph
    -1.57
    ensable
    -1.52
    icted
    -1.52
    ?????-
    -1.51
    ophon
    -1.46
    UCT
    -1.44
    tained
    -1.41
    apter
    -1.40
     transpired
    -1.37
    POSITIVE LOGITS
     differently
    1.79
     everyday
    1.73
     every
    1.67
     whereas
    1.62
     Mondays
    1.61
     Fridays
    1.54
    every
    1.53
     whenever
    1.52
    often
    1.48
     constantly
    1.47
    Activations Density 0.452%

    No Known Activations