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. 14636
    Prev
    Next
    INDEX
    Explanations

    the installation and activation processes related to plugin compatibility issues

    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
    0:0.20
    1:0.08
    2:0.05
    3:0.04
    4:0.10
    5:0.03
    6:0.08
    7:0.09
    8:0.02
    9:0.04
    10:0.12
    11:0.08
    Negative Logits
     marg
    -3.48
    \\\\\\\\
    -3.26
     Mace
    -3.15
     McGregor
    -3.13
     Maver
    -3.11
    uador
    -3.08
     Yemeni
    -3.06
    milo
    -2.94
    aeda
    -2.91
     McKenzie
    -2.90
    POSITIVE LOGITS
     OCD
    9.03
     obsessive
    5.84
     compuls
    5.69
     obs
    5.38
     DSM
    4.48
     ADHD
    3.98
     anxiety
    3.80
     Anxiety
    3.77
     Symptoms
    3.69
     schizophrenia
    3.68
    Activations Density 0.001%

    No Known Activations