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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18617
    Prev
    Next
    INDEX
    Explanations

    references to age demographics and age-related statistics

    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
    0:0.05
    1:0.02
    2:0.10
    3:0.48
    4:0.02
    5:0.09
    6:0.02
    7:0.04
    8:0.02
    9:0.01
    10:0.08
    11:0.01
    Negative Logits
    forcement
    -2.19
     bulldo
    -1.98
     Destination
    -1.95
     Feedback
    -1.84
     Puppet
    -1.81
     Operation
    -1.80
     auction
    -1.79
     Spotlight
    -1.77
     Grail
    -1.76
    Gate
    -1.75
    POSITIVE LOGITS
     age
    3.47
     sexes
    3.33
     younger
    3.31
     genders
    3.29
     aged
    3.17
     males
    3.14
     unmarried
    2.98
     married
    2.97
     teens
    2.94
     ages
    2.91
    Activations Density 1.187%

    No Known Activations