© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 25524
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting indicators in code

    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
    0:0.14
    1:0.14
    2:0.05
    3:0.06
    4:0.04
    5:0.15
    6:0.07
    7:0.04
    8:0.09
    9:0.06
    10:0.06
    11:0.05
    Negative Logits
     sponsors
    -1.79
     concession
    -1.77
     registrations
    -1.64
     negotiator
    -1.63
     resolutions
    -1.62
     volunt
    -1.61
     stabilization
    -1.60
     concessions
    -1.60
     penalty
    -1.56
     resettlement
    -1.55
    POSITIVE LOGITS
    DragonMagazine
    2.30
    MpServer
    2.13
    anu
    1.96
     Reloaded
    1.96
    SourceFile
    1.92
    BBC
    1.88
    Unknown
    1.86
    Filename
    1.83
    Scene
    1.80
    Anonymous
    1.80
    Activations Density 0.000%

    No Known Activations