© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 20741
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental and socioeconomic factors affecting energy and infrastructure

    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
    0:0.06
    1:0.01
    2:0.07
    3:0.40
    4:0.02
    5:0.07
    6:0.01
    7:0.08
    8:0.06
    9:0.01
    10:0.10
    11:0.04
    Negative Logits
     Dreams
    -2.58
    isode
    -2.58
     �
    -2.53
    Truth
    -2.51
    Happy
    -2.43
     �
    -2.43
    Laughs
    -2.34
    Beat
    -2.32
    aughs
    -2.31
    ????????
    -2.31
    POSITIVE LOGITS
     cumbers
    3.69
     reliance
    3.43
     limitations
    3.41
     attrition
    3.40
     constraints
    3.40
     reluctance
    3.38
     restrictions
    3.35
     geographic
    3.25
     geographical
    3.24
     heterogeneity
    3.19
    Activations Density 0.877%

    No Known Activations