© 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. 9-ATT-KK
    11. 24196
    Prev
    Next
    INDEX
    Explanations

    elements related to character relationships and connections within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.04
    2:0.09
    3:0.06
    4:0.04
    5:0.07
    6:0.13
    7:0.04
    8:0.21
    9:0.12
    10:0.02
    11:0.03
    Negative Logits
     Wiggins
    -3.94
     Huck
    -3.56
     Kear
    -3.50
    ��
    -3.48
     ski
    -3.46
     Sloven
    -3.35
    oultry
    -3.16
    Kansas
    -3.16
     Roose
    -3.12
     skiing
    -3.10
    POSITIVE LOGITS
     Persona
    8.73
     Atl
    5.04
    Atl
    4.54
     Lilith
    4.40
     Makoto
    4.37
     Maya
    4.09
     Shiva
    4.08
    awaru
    4.04
     Hades
    4.04
     Grimoire
    3.98
    Activations Density 0.003%

    No Known Activations