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. 5-ATT-KK
    6. 28169
    Prev
    Next
    INDEX
    Explanations

    statements related to research findings and implications in scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    2:0.05
    3:0.15
    4:0.05
    5:0.06
    6:0.02
    7:0.04
    8:0.06
    9:0.14
    10:0.20
    11:0.13
    Negative Logits
    Yep
    -1.30
    ascript
    -1.27
    sembly
    -1.24
    76561
    -1.21
     Anyway
    -1.20
    Yeah
    -1.18
    VIDEO
    -1.18
    Okay
    -1.17
     Alright
    -1.16
    >)
    -1.15
    POSITIVE LOGITS
     empir
    1.42
     underest
    1.41
     phylogen
    1.39
     qualitative
    1.38
     clinically
    1.36
     statistically
    1.33
     ∼
    1.32
     observed
    1.30
     PLoS
    1.30
     caus
    1.29
    Activations Density 0.158%

    No Known Activations