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. 18711
    Prev
    Next
    INDEX
    Explanations

    terms related to programming concepts, specifically referencing data passing methodologies

    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
    1:0.09
    2:0.08
    3:0.08
    4:0.08
    5:0.07
    6:0.07
    7:0.07
    8:0.08
    9:0.09
    10:0.08
    11:0.07
    Negative Logits
     CCP
    -2.94
    ammed
    -2.88
     Eid
    -2.86
     AH
    -2.82
     Guam
    -2.77
     GST
    -2.75
     EA
    -2.70
     CD
    -2.65
     ACA
    -2.63
     Sins
    -2.58
    POSITIVE LOGITS
    rawdownloadcloneembedreportprint
    3.22
    Connell
    2.93
    RFC
    2.88
    zag
    2.86
    quart
    2.77
    arrow
    2.73
    compan
    2.72
    join
    2.72
    arry
    2.71
    leon
    2.71
    Activations Density 0.000%

    No Known Activations