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. 9-ATT-KK
    6. 20698
    Prev
    Next
    INDEX
    Explanations

    references to drug testing and substances related to violations in sports

    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
    2:0.30
    3:0.12
    4:0.03
    5:0.16
    6:0.03
    7:0.05
    8:0.03
    9:0.04
    10:0.04
    11:0.01
    Negative Logits
     retreat
    -2.21
     retreating
    -2.03
    Theme
    -2.01
     tribute
    -1.99
     lured
    -1.96
    EStreamFrame
    -1.90
     lull
    -1.89
     metaphor
    -1.89
    Wars
    -1.89
     homelessness
    -1.89
    POSITIVE LOGITS
     tests
    4.27
     testing
    3.87
     test
    3.75
     inspections
    3.73
     tested
    3.71
     Testing
    3.69
     Tests
    3.65
     inspected
    3.63
     inspection
    3.62
    Testing
    3.42
    Activations Density 0.525%

    No Known Activations