© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 37550
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the need or opportunity for action or intervention

    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
    2:0.14
    3:0.12
    4:0.13
    5:0.02
    6:0.05
    7:0.23
    8:0.03
    9:0.03
    10:0.05
    11:0.11
    Negative Logits
     eleph
    -1.52
    foundland
    -1.51
    arian
    -1.45
     Labrador
    -1.45
    nesday
    -1.41
     mosqu
    -1.36
     occas
    -1.35
    ERC
    -1.34
    arta
    -1.34
    ordial
    -1.32
    POSITIVE LOGITS
    Movie
    1.41
    Choice
    1.34
     overt
    1.26
    Reviewer
    1.24
     bleed
    1.23
     overall
    1.22
    ories
    1.21
     viewers
    1.21
     verification
    1.20
     negotiators
    1.20
    Activations Density 0.012%

    No Known Activations