© 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. 5-ATT-KK
    11. 40033
    Prev
    Next
    INDEX
    Explanations

    terms related to sports gameplay mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    0:0.02
    1:0.02
    2:0.11
    3:0.03
    4:0.09
    5:0.02
    6:0.05
    7:0.31
    8:0.03
    9:0.03
    10:0.19
    11:0.04
    Negative Logits
    erity
    -1.81
    osponsors
    -1.78
    ngth
    -1.76
    ept
    -1.72
    amina
    -1.71
    ritis
    -1.70
    encies
    -1.69
    fect
    -1.63
    ique
    -1.62
    fol
    -1.62
    POSITIVE LOGITS
     Curve
    1.71
     Parade
    1.71
    lane
    1.69
     elevator
    1.61
     hallway
    1.56
     Cipher
    1.55
     mismatch
    1.52
     gates
    1.50
     proposition
    1.50
     aloud
    1.48
    Activations Density 0.001%

    No Known Activations