© 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. 41162
    Prev
    Next
    INDEX
    Explanations

    recurring themes and activities related to events in narratives

    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
    0:0.06
    1:0.08
    2:0.03
    3:0.03
    4:0.03
    5:0.39
    6:0.03
    7:0.02
    8:0.07
    9:0.06
    10:0.10
    11:0.05
    Negative Logits
    role
    -1.77
     Saras
    -1.59
    SY
    -1.58
    annabin
    -1.58
    agher
    -1.56
    rious
    -1.56
    capacity
    -1.56
     homegrown
    -1.55
    BIL
    -1.55
     ILCS
    -1.53
    POSITIVE LOGITS
    Cooldown
    2.08
    iversary
    1.91
     Procedures
    1.86
    cember
    1.85
     chores
    1.80
     [|
    1.74
    EGIN
    1.74
    ogue
    1.72
     session
    1.72
     deadline
    1.71
    Activations Density 0.532%

    No Known Activations