© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 41608
    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
    0:0.03
    1:0.02
    2:0.21
    3:0.11
    4:0.18
    5:0.04
    6:0.06
    7:0.06
    8:0.06
    9:0.04
    10:0.07
    11:0.06
    Negative Logits
     Cosponsors
    -2.43
     Berserker
    -1.60
     rash
    -1.56
     intrusion
    -1.53
     stimuli
    -1.48
     transmissions
    -1.48
     Condition
    -1.47
     Processor
    -1.47
     sarc
    -1.46
     Viktor
    -1.46
    POSITIVE LOGITS
    joice
    2.17
    consider
    2.13
    iddy
    1.90
    veland
    1.88
     beware
    1.87
    enfranch
    1.84
    liam
    1.77
     bragging
    1.75
    lee
    1.74
     rejoice
    1.74
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.