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. 3-ATT-KK
    6. 7911
    Prev
    Next
    INDEX
    Explanations

    mentions of social media interactions and engagement

    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
    0:0.02
    1:0.12
    2:0.06
    3:0.03
    4:0.02
    5:0.06
    6:0.05
    7:0.05
    8:0.04
    9:0.35
    10:0.08
    11:0.06
    Negative Logits
    terday
    -1.53
     unaccount
    -1.46
    intestinal
    -1.31
    $
    -1.30
     bragging
    -1.30
    tons
    -1.27
     dwar
    -1.24
    too
    -1.24
    cot
    -1.24
     depended
    -1.23
    POSITIVE LOGITS
     embed
    1.39
     closely
    1.32
     newsletters
    1.29
     blockers
    1.25
    ulations
    1.25
     carefully
    1.23
    BBC
    1.22
    ":[
    1.21
    Patch
    1.21
    Links
    1.20
    Activations Density 0.024%

    No Known Activations