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. 13843
    Prev
    Next
    INDEX
    Explanations

    locations where individuals have grown up and descriptive details about these locations, such as cities and environmental factors

    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
    0:0.09
    1:0.03
    2:0.09
    3:0.08
    4:0.08
    5:0.08
    6:0.04
    7:0.03
    8:0.16
    9:0.12
    10:0.08
    11:0.04
    Negative Logits
    soDeliveryDate
    -1.31
    ��
    -1.31
    mbuds
    -1.26
    emort
    -1.21
    etsk
    -1.19
    mble
    -1.18
    odan
    -1.16
    ccess
    -1.15
    装
    -1.14
    в
    -1.12
    POSITIVE LOGITS
     adolesc
    1.59
     leaps
    1.37
    \">
    1.36
     BASE
    1.21
     tuberculosis
    1.15
     Trance
    1.12
     Volunte
    1.11
     LSD
    1.09
    ZE
    1.08
     weekends
    1.05
    Activations Density 0.023%

    No Known Activations