© 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. 25305
    Prev
    Next
    INDEX
    Explanations

    instances of reported speech or quotes

    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
    0:0.03
    1:0.03
    2:0.06
    3:0.12
    4:0.09
    5:0.05
    6:0.10
    7:0.06
    8:0.06
    9:0.08
    10:0.18
    11:0.08
    Negative Logits
     registrations
    -1.38
     upstream
    -1.37
     downstream
    -1.36
     calibration
    -1.34
     runoff
    -1.34
     precursor
    -1.33
     interfering
    -1.32
     migrating
    -1.32
     prelim
    -1.32
     discord
    -1.29
    POSITIVE LOGITS
    Laughs
    1.73
    ヴ
    1.68
    laughs
    1.65
    laugh
    1.65
    ディ
    1.63
    ushed
    1.61
    uphem
    1.60
     laughed
    1.59
     laughs
    1.55
     ].
    1.55
    Activations Density 0.042%

    No Known Activations