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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 2656
    Prev
    Next
    INDEX
    Explanations

    financial and technology-related management topics, particularly within the automotive industry

    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
    0:0.24
    1:0.02
    2:0.12
    3:0.06
    4:0.02
    5:0.08
    6:0.04
    7:0.05
    8:0.25
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
    Ireland
    -4.45
    Irish
    -4.23
     Gael
    -3.83
    Catholic
    -3.80
     Irish
    -3.73
     bishops
    -3.71
     Ulster
    -3.60
     Okin
    -3.59
     Ireland
    -3.50
     Dublin
    -3.46
    POSITIVE LOGITS
     Tesla
    7.76
    Tesla
    7.35
     Elon
    5.99
     Musk
    5.97
     Model
    5.31
     lithium
    4.74
     Frem
    4.53
     SpaceX
    4.11
     kWh
    4.07
     Nikola
    3.92
    Activations Density 0.060%

    No Known Activations