© 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. 45144
    Prev
    Next
    INDEX
    Explanations

    terms related to virtual currencies and their regulation

    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
    1:0.01
    2:0.05
    3:0.07
    4:0.04
    5:0.07
    6:0.05
    7:0.05
    8:0.03
    9:0.07
    10:0.36
    11:0.12
    Negative Logits
     Claud
    -1.62
     flask
    -1.54
    senal
    -1.48
     linen
    -1.47
     Uniform
    -1.46
     Bourbon
    -1.44
     Fram
    -1.44
    ÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂ
    -1.43
     microbi
    -1.42
     Inspect
    -1.42
    POSITIVE LOGITS
     Chaser
    1.83
    arenthood
    1.75
    rage
    1.66
    aber
    1.65
    rencies
    1.65
    ocry
    1.64
    unic
    1.62
     launcher
    1.61
     derivatives
    1.58
    owered
    1.54
    Activations Density 0.006%

    No Known Activations