© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 39845
    Prev
    Next
    INDEX
    Explanations

    high-performance baseball pitching attributes and statistics

    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
    0:0.06
    1:0.02
    2:0.07
    3:0.06
    4:0.06
    5:0.07
    6:0.04
    7:0.04
    8:0.03
    9:0.09
    10:0.31
    11:0.09
    Negative Logits
     enlist
    -1.74
     indoctr
    -1.72
     murdered
    -1.57
     reun
    -1.51
     cens
    -1.48
    alse
    -1.47
     Democracy
    -1.46
     crem
    -1.46
     UNESCO
    -1.45
     intervened
    -1.42
    POSITIVE LOGITS
     penet
    1.63
     cones
    1.63
     thickness
    1.59
     stationary
    1.56
    DAQ
    1.54
     positional
    1.52
    inventoryQuantity
    1.52
     cone
    1.51
    Range
    1.51
     pads
    1.51
    Activations Density 0.012%

    No Known Activations