Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10156
    Prev
    Next
    INDEX
    Explanations

    references to hometowns and local identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.06
    3:0.10
    4:0.02
    5:0.05
    6:0.06
    7:0.21
    8:0.05
    9:0.05
    10:0.09
    11:0.21
    Negative Logits
    neau
    -1.47
    ersen
    -1.45
    anium
    -1.26
    mentation
    -1.21
     penetration
    -1.14
    erson
    -1.14
     explanations
    -1.13
     motions
    -1.13
    heimer
    -1.10
    farious
    -1.10
    POSITIVE LOGITS
    aukee
    1.33
    atl
    1.19
     hometown
    1.18
    oples
    1.13
    nil
    1.10
     Workers
    1.10
    population
    1.09
     Saras
    1.09
     Athens
    1.08
    localhost
    1.07
    Activations Density 0.006%

    No Known Activations