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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10667
    Prev
    Next
    INDEX
    Explanations

    references or discussions about the experiences and growth over time

    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
    0:0.06
    1:0.05
    2:0.08
    3:0.23
    4:0.04
    5:0.09
    6:0.03
    7:0.13
    8:0.03
    9:0.03
    10:0.16
    11:0.01
    Negative Logits
    Administ
    -2.11
    Completed
    -2.09
    �
    -2.01
    ��
    -2.01
    Reviewer
    -1.99
     Sector
    -1.99
     Buildings
    -1.98
     Forestry
    -1.98
    ,,,,
    -1.97
    Statement
    -1.96
    POSITIVE LOGITS
     decreases
    2.25
     sharper
    2.25
    lier
    2.24
     easier
    2.23
     underest
    2.17
     quicker
    2.16
     harder
    2.14
     richer
    2.14
     increases
    2.11
     harsher
    2.10
    Activations Density 0.033%

    No Known Activations