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. 10618
    Prev
    Next
    INDEX
    Explanations

    information related to Alzheimer's disease and its associations with health studies

    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
    0:0.11
    1:0.02
    2:0.31
    3:0.07
    4:0.03
    5:0.09
    6:0.05
    7:0.04
    8:0.10
    9:0.07
    10:0.02
    11:0.04
    Negative Logits
     pussy
    -3.08
     crotch
    -3.04
     Lesbian
    -3.04
     lesbians
    -3.00
     Zoro
    -2.98
    iannopoulos
    -2.98
    LGBT
    -2.94
     queer
    -2.93
     BDS
    -2.89
    Sex
    -2.88
    POSITIVE LOGITS
     Alzheimer
    6.78
     dementia
    6.22
     Alz
    5.00
     dement
    3.96
     Neurolog
    3.84
     cognitive
    3.80
     plaque
    3.74
     Memory
    3.67
     Cognitive
    3.61
     Parkinson
    3.61
    Activations Density 0.025%

    No Known Activations