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. 6253
    Prev
    Next
    INDEX
    Explanations

    repetitive sequences containing specific characters

    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
    0:0.07
    1:0.09
    2:0.07
    3:0.04
    4:0.05
    5:0.20
    6:0.08
    7:0.07
    8:0.06
    9:0.08
    10:0.06
    11:0.08
    Negative Logits
     compan
    -1.46
     Tycoon
    -1.34
    hovah
    -1.27
     trave
    -1.26
    kefeller
    -1.26
     assum
    -1.25
     horizont
    -1.25
     perspect
    -1.25
     pse
    -1.24
     psychiat
    -1.24
    POSITIVE LOGITS
    forth
    1.52
    trigger
    1.44
    unin
    1.41
    PART
    1.41
    Marginal
    1.40
    delete
    1.36
    sound
    1.36
    cake
    1.35
    heim
    1.31
     Butterfly
    1.29
    Activations Density 0.001%

    No Known Activations