© 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. 30136
    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
    0:0.06
    1:0.06
    2:0.09
    3:0.09
    4:0.08
    5:0.06
    6:0.07
    7:0.08
    8:0.05
    9:0.06
    10:0.10
    11:0.13
    Negative Logits
     relativity
    -2.80
     physics
    -2.60
     realities
    -2.57
     concepts
    -2.56
     theor
    -2.37
     fictional
    -2.35
     philosophers
    -2.35
     universes
    -2.33
     worlds
    -2.31
     timelines
    -2.25
    POSITIVE LOGITS
    mble
    2.58
    ratulations
    2.47
    iscons
    2.41
    akia
    2.36
    ignant
    2.31
    odox
    2.28
    adra
    2.25
    cknow
    2.22
    orum
    2.18
    isite
    2.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.