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. 476
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and their associated professions or contributions

    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
    0:0.04
    1:0.01
    2:0.04
    3:0.57
    4:0.03
    5:0.06
    6:0.02
    7:0.05
    8:0.02
    9:0.01
    10:0.07
    11:0.01
    Negative Logits
     partitions
    -2.56
     residences
    -2.55
     checkpoints
    -2.51
     arrangements
    -2.50
     iPads
    -2.42
     exits
    -2.41
     packages
    -2.40
     apartments
    -2.40
     assemblies
    -2.40
     entrances
    -2.39
    POSITIVE LOGITS
     enthusiast
    3.42
     lover
    3.38
     scholar
    3.22
    ologist
    3.12
     campaigner
    3.06
     performer
    3.06
     musician
    3.06
    writer
    3.05
     educator
    3.04
     believer
    3.03
    Activations Density 1.532%

    No Known Activations