© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 21714
    Prev
    Next
    INDEX
    Explanations

    references to actors and their roles in film and television

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.05
    2:0.13
    3:0.07
    4:0.04
    5:0.12
    6:0.02
    7:0.03
    8:0.17
    9:0.17
    10:0.06
    11:0.03
    Negative Logits
    sembly
    -1.51
    igent
    -1.50
    ividual
    -1.37
    merce
    -1.37
     subsistence
    -1.32
    Frameworks
    -1.28
     gist
    -1.24
     Sections
    -1.22
     Territories
    -1.21
    fficient
    -1.20
    POSITIVE LOGITS
     Ridley
    1.56
    otto
    1.32
     HBO
    1.31
     Oscar
    1.30
    love
    1.29
     movies
    1.25
     blockbuster
    1.25
     Celebrity
    1.25
     premie
    1.25
    CTV
    1.23
    Activations Density 0.031%

    No Known Activations