© 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. 46954
    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
    3:0.08
    4:0.08
    5:0.09
    6:0.09
    7:0.08
    8:0.08
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
     Toll
    -1.81
    ティ
    -1.73
    ーテ
    -1.68
    rencies
    -1.68
    zsche
    -1.57
     methodological
    -1.56
    cent
    -1.55
     Accounts
    -1.52
     Cosponsors
    -1.52
     Ples
    -1.51
    POSITIVE LOGITS
    ?).
    1.79
    viol
    1.78
    ModLoader
    1.66
     indign
    1.65
    aston
    1.64
     disob
    1.63
    VO
    1.62
    ?)
    1.60
     fixme
    1.57
     disobedience
    1.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.