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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22315
    Prev
    Next
    INDEX
    Explanations

    references to films and video content, particularly in connection to sports and documentaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.03
    2:0.04
    3:0.07
    4:0.04
    5:0.08
    6:0.03
    7:0.03
    8:0.39
    9:0.07
    10:0.07
    11:0.03
    Negative Logits
     recol
    -1.32
    RP
    -1.23
    RC
    -1.22
     ⓘ
    -1.19
    ainers
    -1.15
     Precision
    -1.15
     sourcing
    -1.12
     collaborators
    -1.09
     aliases
    -1.09
     Option
    -1.07
    POSITIVE LOGITS
     unfold
    1.94
    flix
    1.61
     deterior
    1.50
     cartoons
    1.39
     closely
    1.35
     evolve
    1.31
     aloud
    1.29
     prosper
    1.25
     commercials
    1.24
    clips
    1.20
    Activations Density 0.065%

    No Known Activations