© 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. 7803
    Prev
    Next
    INDEX
    Explanations

    references to psychological and behavioral concepts related to habit formation and addiction

    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
    0:0.38
    1:0.03
    2:0.05
    3:0.07
    4:0.06
    5:0.04
    6:0.04
    7:0.01
    8:0.04
    9:0.09
    10:0.09
    11:0.05
    Negative Logits
     equivalent
    -2.18
    BuyableInstoreAndOnline
    -1.82
     equivalents
    -1.74
     Territory
    -1.53
     evenly
    -1.46
    Located
    -1.45
     decoration
    -1.44
     Inferno
    -1.44
    ItemThumbnailImage
    -1.43
     escalate
    -1.41
    POSITIVE LOGITS
    quist
    2.16
    baugh
    2.10
    sein
    2.09
    ondo
    2.08
    witz
    2.08
    osa
    2.05
    aro
    2.04
    bard
    2.04
    hart
    2.03
    ijk
    2.01
    Activations Density 0.045%

    No Known Activations