© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 40186
    Prev
    Next
    INDEX
    Explanations

    themes related to community and social interactions

    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
    2:0.16
    3:0.20
    4:0.14
    5:0.02
    6:0.04
    7:0.10
    8:0.04
    9:0.04
    10:0.09
    11:0.07
    Negative Logits
     insofar
    -1.45
     Editors
    -1.42
     Contributions
    -1.38
     precedent
    -1.35
     Reserved
    -1.33
     referral
    -1.32
     Investment
    -1.32
     Yao
    -1.31
     Founding
    -1.31
     attribution
    -1.31
    POSITIVE LOGITS
    rily
    1.82
     unfold
    1.70
    romptu
    1.66
    iless
    1.64
     unfolded
    1.58
    ]]
    1.51
     ])
    1.47
    pless
    1.47
    aughs
    1.45
     calmly
    1.45
    Activations Density 0.253%

    No Known Activations