Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44010
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.05
    2:0.08
    3:0.07
    4:0.08
    5:0.08
    6:0.09
    7:0.08
    8:0.08
    9:0.09
    10:0.08
    11:0.08
    Negative Logits
     ribbon
    -1.53
     distinction
    -1.53
    natureconservancy
    -1.49
     hierarch
    -1.48
    quickShipAvailable
    -1.46
     introductory
    -1.45
     rarity
    -1.45
     sim
    -1.44
     precedent
    -1.43
     immutable
    -1.43
    POSITIVE LOGITS
    ascus
    1.72
    ash
    1.68
    renches
    1.68
    uggage
    1.61
    acht
    1.56
    agan
    1.52
    rough
    1.52
    ester
    1.50
    igon
    1.47
    ÃÂ
    1.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.