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. 2-ATT-KK
    6. 22244
    Prev
    Next
    INDEX
    Explanations

    adverbial expressions of frequency

    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
    0:0.05
    1:0.02
    2:0.07
    3:0.22
    4:0.26
    5:0.05
    6:0.05
    7:0.01
    8:0.07
    9:0.08
    10:0.05
    11:0.02
    Negative Logits
    wake
    -1.53
    buster
    -1.37
    gypt
    -1.33
    wash
    -1.32
    quote
    -1.30
    Haunted
    -1.29
    isman
    -1.28
    intosh
    -1.27
    bowl
    -1.25
    iewicz
    -1.24
    POSITIVE LOGITS
     exceptions
    1.60
     plenty
    1.50
    cium
    1.47
    everal
    1.43
     Canaver
    1.39
     overlap
    1.38
     variability
    1.32
     vacancies
    1.31
    nces
    1.30
    athi
    1.28
    Activations Density 0.066%

    No Known Activations