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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10039
    Prev
    Next
    INDEX
    Explanations

    names of countries and capitals

    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
    0:0.03
    1:0.08
    2:0.09
    3:0.10
    4:0.05
    5:0.07
    6:0.10
    7:0.12
    8:0.06
    9:0.06
    10:0.11
    11:0.08
    Negative Logits
     Collider
    -1.19
     Euph
    -1.11
    wake
    -1.09
     ACTIONS
    -1.08
    Keefe
    -1.06
    Bloom
    -1.05
     Hud
    -1.04
     reverber
    -1.04
     Scor
    -1.03
    Crystal
    -1.01
    POSITIVE LOGITS
     domain
    1.07
     1897
    1.07
     residence
    1.06
     fluent
    1.05
     Guam
    1.03
    age
    1.02
     1880
    1.02
     guessed
    1.01
     DISTRICT
    0.99
     1961
    0.99
    Activations Density 0.002%

    No Known Activations