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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 28526
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    0:0.08
    1:0.07
    2:0.08
    3:0.07
    4:0.08
    5:0.09
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
    emia
    -1.66
     Photographer
    -1.55
     Casting
    -1.55
     Narr
    -1.54
    atched
    -1.53
     Friendship
    -1.52
     Opinion
    -1.48
     Salon
    -1.48
    wen
    -1.48
     Rory
    -1.47
    POSITIVE LOGITS
    inventoryQuantity
    1.81
    ModLoader
    1.76
    natureconservancy
    1.74
    sers
    1.73
    ══
    1.70
    ciation
    1.69
    quickShipAvailable
    1.69
    actionDate
    1.65
    catentry
    1.64
    ciples
    1.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.