© 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. 33432
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.05
    1:0.02
    2:0.13
    3:0.10
    4:0.20
    5:0.06
    6:0.06
    7:0.06
    8:0.11
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
    ries
    -1.53
     holdings
    -1.44
    urst
    -1.40
    onement
    -1.33
    adan
    -1.33
    idium
    -1.32
     dates
    -1.32
     Capitol
    -1.30
     commemor
    -1.26
    resa
    -1.23
    POSITIVE LOGITS
     Logged
    1.81
     sooner
    1.52
    Reason
    1.41
     wiser
    1.40
     Alone
    1.38
     liking
    1.37
     anyways
    1.36
    Higher
    1.35
     outweigh
    1.34
    ificantly
    1.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.