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. 28030
    Prev
    Next
    INDEX
    Explanations

    references to public policy and social issues in different regions

    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
    0:0.10
    1:0.01
    2:0.15
    3:0.13
    4:0.05
    5:0.02
    6:0.05
    7:0.08
    8:0.10
    9:0.05
    10:0.09
    11:0.11
    Negative Logits
    forth
    -1.64
    tein
    -1.50
    process
    -1.47
     resumed
    -1.45
     conven
    -1.45
     adjourn
    -1.43
     commence
    -1.41
     stalled
    -1.41
     convened
    -1.34
     routine
    -1.32
    POSITIVE LOGITS
    "]
    1.73
    "},"
    1.73
    の�
    1.73
     inherit
    1.73
    エル
    1.68
    aceae
    1.68
    "],"
    1.59
    }"
    1.56
    isine
    1.49
     Tags
    1.44
    Activations Density 0.003%

    No Known Activations