© 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. 43615
    Prev
    Next
    INDEX
    Explanations

    actions related to arrangement and organization

    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
    0:0.03
    1:0.01
    2:0.08
    3:0.11
    4:0.19
    5:0.03
    6:0.05
    7:0.23
    8:0.02
    9:0.05
    10:0.07
    11:0.08
    Negative Logits
    attribute
    -1.69
    .?
    -1.66
    advertising
    -1.66
    xual
    -1.56
     compared
    -1.56
    etheless
    -1.49
     awa
    -1.48
    inventoryQuantity
    -1.47
    lda
    -1.47
    wow
    -1.47
    POSITIVE LOGITS
     refund
    1.49
     evacuation
    1.44
     shipment
    1.41
     disembark
    1.38
     Headquarters
    1.37
     vans
    1.36
     cease
    1.35
     copies
    1.34
     crews
    1.34
     Installation
    1.33
    Activations Density 0.001%

    No Known Activations