Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14653
    Prev
    Next
    INDEX
    Explanations

    design principles related to text formatting and presentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.08
    2:0.08
    3:0.04
    4:0.05
    5:0.02
    6:0.13
    7:0.17
    8:0.02
    9:0.03
    10:0.05
    11:0.16
    Negative Logits
     Sheldon
    -2.69
    romeda
    -2.43
     Probe
    -2.35
     Noon
    -2.33
     Sands
    -2.33
     Shuttle
    -2.30
     Frontier
    -2.29
    ederation
    -2.22
     preparations
    -2.19
     Crack
    -2.17
    POSITIVE LOGITS
     attribute
    4.70
     attributes
    4.62
    Attribute
    4.16
    attr
    3.94
    attribute
    3.89
     Attributes
    3.82
    Attributes
    3.75
     att
    2.74
     assigns
    2.70
     descriptor
    2.64
    Activations Density 0.009%

    No Known Activations