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. 3-ATT-KK
    6. 8313
    Prev
    Next
    INDEX
    Explanations

    references to social relationships and dynamics, particularly relating to equality, rights, and familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.07
    2:0.05
    3:0.02
    4:0.04
    5:0.35
    6:0.09
    7:0.05
    8:0.05
    9:0.04
    10:0.10
    11:0.04
    Negative Logits
    Phase
    -1.80
    imation
    -1.70
    tracking
    -1.68
    pletion
    -1.61
    ometry
    -1.61
    osure
    -1.60
    Constructed
    -1.60
    ongo
    -1.58
    oulos
    -1.56
     CRC
    -1.54
    POSITIVE LOGITS
    their
    3.15
     theirs
    2.81
     THEIR
    2.57
    They
    2.38
    Their
    2.37
     THEY
    2.33
    they
    2.25
     their
    2.19
     They
    2.17
     Their
    2.17
    Activations Density 0.390%

    No Known Activations