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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 22346
    Prev
    Next
    INDEX
    Explanations

    technical instructions related to Docker and file management

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.06
    1:0.11
    2:0.04
    3:0.07
    4:0.04
    5:0.06
    6:0.10
    7:0.11
    8:0.06
    9:0.07
    10:0.16
    11:0.08
    Negative Logits
    光
    -1.32
     Rudd
    -1.28
     Rebell
    -1.17
    arians
    -1.17
    ‎
    -1.17
     Stalin
    -1.16
     succumbed
    -1.14
    olitics
    -1.12
    ウ
    -1.08
    judicial
    -1.08
    POSITIVE LOGITS
     Configuration
    1.73
     Setup
    1.65
     plugin
    1.62
     initialization
    1.62
     Authentication
    1.59
    Apply
    1.58
     Example
    1.54
     configure
    1.53
     backend
    1.51
     wrapper
    1.50
    Activations Density 0.412%

    No Known Activations