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. 9-ATT-KK
    6. 18665
    Prev
    Next
    INDEX
    Explanations

    phrases related to investments and economic support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.02
    2:0.05
    3:0.23
    4:0.02
    5:0.21
    6:0.02
    7:0.06
    8:0.03
    9:0.02
    10:0.18
    11:0.03
    Negative Logits
     invoice
    -2.57
     quotas
    -2.56
     condol
    -2.48
     allowance
    -2.36
     vetoed
    -2.35
     condesc
    -2.33
     veto
    -2.29
    =-=-
    -2.27
     acknowled
    -2.27
    galitarian
    -2.26
    POSITIVE LOGITS
     technology
    2.73
     technologies
    2.71
    technology
    2.65
     improvements
    2.61
    proven
    2.51
     improvement
    2.38
    ️
    2.36
    Dash
    2.34
     skills
    2.32
     improving
    2.28
    Activations Density 0.022%

    No Known Activations