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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3137
    Prev
    Next
    INDEX
    Explanations

    instructions related to software installation and configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.03
    2:0.06
    3:0.29
    4:0.04
    5:0.17
    6:0.05
    7:0.03
    8:0.06
    9:0.05
    10:0.05
    11:0.04
    Negative Logits
     flu
    -1.98
     ­
    -1.86
     salute
    -1.85
     counted
    -1.84
     clearance
    -1.70
     estimated
    -1.69
     Morse
    -1.69
     tallied
    -1.68
     estimate
    -1.66
     exaggeration
    -1.65
    POSITIVE LOGITS
    cfg
    2.66
    modules
    2.65
    resources
    2.54
    plugins
    2.50
    rc
    2.41
    src
    2.40
    sites
    2.40
    scripts
    2.38
    framework
    2.30
    assets
    2.28
    Activations Density 0.256%

    No Known Activations