© 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. 45879
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and interconnectedness among characters

    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
    0:0.01
    1:0.02
    2:0.10
    3:0.10
    4:0.28
    5:0.04
    6:0.04
    7:0.16
    8:0.03
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
    lot
    -1.74
    perate
    -1.64
    isd
    -1.60
    lap
    -1.57
    iversal
    -1.56
    ONY
    -1.52
    iesta
    -1.45
     Cogn
    -1.44
    ondo
    -1.44
    mble
    -1.43
    POSITIVE LOGITS
    SpaceEngineers
    1.77
     perceived
    1.66
     ideals
    1.64
     freedoms
    1.63
     Brotherhood
    1.54
    worms
    1.53
     pronouns
    1.50
     mutants
    1.48
     expressed
    1.46
     tropes
    1.46
    Activations Density 0.060%

    No Known Activations