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. 10613
    Prev
    Next
    INDEX
    Explanations

    numerical and categorical data pertaining to specifications or identifiers

    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
    0:0.05
    1:0.04
    2:0.09
    3:0.15
    4:0.07
    5:0.03
    6:0.10
    7:0.12
    8:0.10
    9:0.05
    10:0.10
    11:0.04
    Negative Logits
    onian
    -0.93
     Survive
    -0.88
    Lens
    -0.87
    rene
    -0.87
    lings
    -0.87
    shall
    -0.86
    ía
    -0.84
     horizont
    -0.84
    onal
    -0.84
    ˈ
    -0.83
    POSITIVE LOGITS
     RPC
    0.88
    araoh
    0.88
     Caps
    0.88
    ymes
    0.81
     Tel
    0.81
     ISBN
    0.81
     auth
    0.80
     Rao
    0.80
     ke
    0.79
     Shib
    0.79
    Activations Density 0.123%

    No Known Activations