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. 13757
    Prev
    Next
    INDEX
    Explanations

    locations described by streets and avenues

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.04
    1:0.02
    2:0.09
    3:0.06
    4:0.43
    5:0.07
    6:0.02
    7:0.02
    8:0.03
    9:0.12
    10:0.04
    11:0.02
    Negative Logits
    syn
    -1.51
    ć
    -1.41
    γ
    -1.39
    WAR
    -1.38
    imen
    -1.37
    GUI
    -1.36
    SY
    -1.35
    depend
    -1.33
    ween
    -1.31
    BIL
    -1.31
    POSITIVE LOGITS
    endment
    1.65
     Misty
    1.60
    imester
    1.60
    eve
    1.51
     anniversary
    1.50
    rollers
    1.49
     Blooming
    1.46
     Macy
    1.29
     responders
    1.26
     Apostles
    1.24
    Activations Density 0.069%

    No Known Activations