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. 6297
    Prev
    Next
    INDEX
    Explanations

    information related to job applications and personal achievements

    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
    0:0.14
    1:0.06
    2:0.04
    3:0.01
    4:0.05
    5:0.33
    6:0.04
    7:0.07
    8:0.02
    9:0.02
    10:0.03
    11:0.13
    Negative Logits
    �
    -1.80
    antha
    -1.60
    pects
    -1.58
    eters
    -1.54
     Son
    -1.53
    stood
    -1.53
    eter
    -1.52
    cies
    -1.51
    creen
    -1.50
     Hermes
    -1.49
    POSITIVE LOGITS
     congr
    1.75
     msec
    1.43
    dry
    1.37
    soft
    1.35
    gnu
    1.34
    RW
    1.33
    MJ
    1.31
    crazy
    1.30
     Blaz
    1.25
    du
    1.24
    Activations Density 0.060%

    No Known Activations