© 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. 37126
    Prev
    Next
    INDEX
    Explanations

    quantities and expressions related to substantial amounts or efforts

    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
    0:0.02
    1:0.02
    2:0.06
    3:0.07
    4:0.13
    5:0.02
    6:0.13
    7:0.27
    8:0.03
    9:0.05
    10:0.07
    11:0.07
    Negative Logits
    soon
    -1.48
    opus
    -1.43
     claimants
    -1.35
    Tele
    -1.32
     formula
    -1.29
    onga
    -1.28
     tide
    -1.27
     allele
    -1.26
    Cro
    -1.25
     tides
    -1.25
    POSITIVE LOGITS
     redes
    1.50
     rehab
    1.49
    ngth
    1.47
     researching
    1.44
     preparing
    1.37
     studying
    1.33
     frivol
    1.32
     designing
    1.32
     optimizing
    1.32
     brainstorm
    1.30
    Activations Density 0.013%

    No Known Activations