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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 1-ATT-KK
    6. 6298
    Prev
    Next
    INDEX
    Explanations

    common preposition 'of'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.36
    1:0.06
    2:0.02
    3:0.01
    4:0.03
    5:0.19
    6:0.03
    7:0.05
    8:0.01
    9:0.01
    10:0.01
    11:0.18
    Negative Logits
    berus
    -1.66
    ERY
    -1.55
    lished
    -1.47
    iencies
    -1.44
    iland
    -1.42
     Lauder
    -1.41
    artifacts
    -1.39
    owship
    -1.37
    =-=-
    -1.34
    Services
    -1.30
    POSITIVE LOGITS
    emonic
    1.65
    undred
    1.39
     GHz
    1.39
    GHz
    1.33
    anova
    1.30
     slice
    1.28
    hillary
    1.27
    inch
    1.27
    achev
    1.27
     pocket
    1.26
    Activations Density 0.098%

    No Known Activations