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. 8490
    Prev
    Next
    INDEX
    Explanations

    references to relationships and interactions between individuals, often highlighting their social dynamics

    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
    0:0.03
    1:0.03
    2:0.14
    3:0.06
    4:0.03
    5:0.06
    6:0.05
    7:0.09
    8:0.22
    9:0.08
    10:0.07
    11:0.10
    Negative Logits
     Unloaded
    -1.19
    arthed
    -1.18
     replaced
    -1.18
     Purg
    -1.16
    ortium
    -1.16
     premiered
    -1.13
    edition
    -1.13
     antidote
    -1.13
     VERS
    -1.06
    ciation
    -1.06
    POSITIVE LOGITS
    omever
    1.19
    amate
    1.12
    rust
    1.07
     disabilities
    1.07
    ��
    1.04
    efe
    1.04
    rouse
    1.03
     colleagues
    1.00
     regard
    1.00
     handlers
    1.00
    Activations Density 0.122%

    No Known Activations