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. 44279
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions, particularly "of" and "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.01
    2:0.06
    3:0.05
    4:0.07
    5:0.02
    6:0.32
    7:0.17
    8:0.03
    9:0.05
    10:0.07
    11:0.05
    Negative Logits
     unfinished
    -1.49
     coffin
    -1.49
    版
    -1.34
    代
    -1.32
    breaks
    -1.29
     Pv
    -1.19
     condol
    -1.16
     NTS
    -1.15
    Dialog
    -1.14
     regrets
    -1.14
    POSITIVE LOGITS
    iani
    1.49
    iuses
    1.43
    osi
    1.38
    omp
    1.38
    encers
    1.33
    uthor
    1.32
    itives
    1.31
    imil
    1.28
    Magn
    1.27
     detect
    1.25
    Activations Density 0.000%

    No Known Activations