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. 7535
    Prev
    Next
    INDEX
    Explanations

    phrases related to life and existence

    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
    0:0.02
    1:0.02
    2:0.09
    3:0.05
    4:0.23
    5:0.02
    6:0.13
    7:0.24
    8:0.03
    9:0.03
    10:0.05
    11:0.04
    Negative Logits
    */(
    -1.68
    Cola
    -1.56
    ortium
    -1.51
     Citation
    -1.50
    stable
    -1.50
     guiIcon
    -1.50
    bernatorial
    -1.45
     Telescope
    -1.39
    Interested
    -1.38
    iculty
    -1.38
    POSITIVE LOGITS
     Venezuel
    1.58
     eternity
    1.51
     fantasies
    1.49
     HELL
    1.49
     adolesc
    1.49
     Millennials
    1.48
     embodied
    1.45
     Khe
    1.42
     dads
    1.41
     Colomb
    1.40
    Activations Density 0.000%

    No Known Activations