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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11411
    Prev
    Next
    INDEX
    Explanations

    references to software distributions and versions, specifically in the context of Linux systems

    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
    0:0.33
    1:0.01
    2:0.13
    3:0.11
    4:0.02
    5:0.07
    6:0.03
    7:0.05
    8:0.10
    9:0.03
    10:0.03
    11:0.03
    Negative Logits
     Harlem
    -2.98
     Guerrero
    -2.81
     NRA
    -2.63
     Garner
    -2.57
     Gaga
    -2.53
    rahim
    -2.47
    Morgan
    -2.45
    encers
    -2.40
    Trigger
    -2.39
     Herrera
    -2.39
    POSITIVE LOGITS
     Linux
    5.43
    Linux
    5.14
     Ubuntu
    5.04
     Debian
    4.89
    linux
    4.76
     CentOS
    4.74
     linux
    4.72
     FreeBSD
    4.63
    kernel
    4.55
     Unix
    4.51
    Activations Density 0.145%

    No Known Activations