© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 37868
    Prev
    Next
    INDEX
    Explanations

    phrases related to the publication process and manuscript preparation

    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
    0:0.07
    1:0.01
    2:0.15
    3:0.15
    4:0.08
    5:0.04
    6:0.02
    7:0.05
    8:0.10
    9:0.05
    10:0.11
    11:0.13
    Negative Logits
     Canaver
    -1.43
     Temper
    -1.38
     Typh
    -1.37
     Perkins
    -1.31
     Ritual
    -1.30
     Bare
    -1.29
     Cohn
    -1.27
     ATL
    -1.26
     Greenberg
    -1.25
     Glas
    -1.25
    POSITIVE LOGITS
    Override
    1.74
    �
    1.61
    fax
    1.61
     nor
    1.61
    EStream
    1.58
    ento
    1.52
    hesda
    1.48
    fml
    1.43
     disclaim
    1.42
    :{
    1.37
    Activations Density 0.000%

    No Known Activations