© 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. 33923
    Prev
    Next
    INDEX
    Explanations

    temporal references and actions that imply sequences or changes in state

    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
    0:0.07
    1:0.04
    2:0.07
    3:0.10
    4:0.09
    5:0.04
    6:0.07
    7:0.04
    8:0.07
    9:0.14
    10:0.14
    11:0.07
    Negative Logits
    overe
    -1.28
     Sovere
    -1.24
     biome
    -1.16
     amen
    -1.16
     lear
    -1.13
     transact
    -1.11
    manufact
    -1.10
     categ
    -1.10
     Subject
    -1.10
     uncond
    -1.09
    POSITIVE LOGITS
    sequently
    1.58
    sequent
    1.44
    Shortly
    1.34
    Attempts
    1.25
     afterward
    1.22
    later
    1.21
    Fast
    1.18
    othy
    1.18
    Then
    1.15
    undo
    1.15
    Activations Density 0.404%

    No Known Activations