© 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. 47251
    Prev
    Next
    INDEX
    Explanations

    terms related to the frequency or prevalence of events or conditions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.11
    3:0.07
    4:0.13
    5:0.05
    6:0.05
    7:0.06
    8:0.03
    9:0.03
    10:0.10
    11:0.27
    Negative Logits
    pox
    -2.06
    raviolet
    -1.91
     flora
    -1.82
     detection
    -1.76
     hairs
    -1.71
    vir
    -1.67
     species
    -1.65
     nickname
    -1.61
    isance
    -1.60
     detect
    -1.60
    POSITIVE LOGITS
    龍喚士
    1.71
    ────
    1.69
    workshop
    1.66
    ────────
    1.65
     withd
    1.63
    prison
    1.62
     Palest
    1.59
     princ
    1.56
    theless
    1.53
    �士
    1.53
    Activations Density 0.004%

    No Known Activations