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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 27563
    Prev
    Next
    INDEX
    Explanations

    references to brands or products related to specific companies or manufacturers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.39
    2:0.03
    3:0.03
    4:0.03
    5:0.18
    6:0.03
    7:0.02
    8:0.05
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
    atile
    -1.79
     Neutral
    -1.73
     Unch
    -1.72
    ratulations
    -1.63
     Detection
    -1.62
    ====
    -1.62
     Adamant
    -1.61
    uberty
    -1.56
     Identity
    -1.54
     Document
    -1.54
    POSITIVE LOGITS
    co
    2.31
     KP
    1.89
    eco
    1.88
    Co
    1.82
     Kon
    1.79
     Co
    1.78
    Ga
    1.77
    rule
    1.76
    FO
    1.73
     Ange
    1.73
    Activations Density 0.003%

    No Known Activations