© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 12385
    Prev
    Next
    INDEX
    Explanations

    key concepts related to startup success and investment strategies

    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
    0:0.39
    1:0.02
    2:0.10
    3:0.08
    4:0.03
    5:0.07
    6:0.03
    7:0.05
    8:0.04
    9:0.03
    10:0.07
    11:0.02
    Negative Logits
     Subaru
    -2.63
     Garr
    -2.55
     alignment
    -2.53
     Schr
    -2.51
     RG
    -2.36
     Metall
    -2.36
    ignment
    -2.34
    shift
    -2.34
    duty
    -2.33
     blues
    -2.31
    POSITIVE LOGITS
     Startup
    3.76
     incub
    3.55
     founders
    3.52
     startup
    3.28
    iOS
    3.14
     IPO
    3.13
    reprene
    3.00
     venture
    2.99
     startups
    2.92
     crowdfunding
    2.92
    Activations Density 0.083%

    No Known Activations