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. 18764
    Prev
    Next
    INDEX
    Explanations

    references to journals and publications within scientific literature

    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
    2:0.06
    3:0.12
    4:0.03
    5:0.19
    6:0.02
    7:0.10
    8:0.06
    9:0.02
    10:0.27
    11:0.02
    Negative Logits
     whichever
    -2.09
     whoever
    -2.02
    fax
    -1.93
    taboola
    -1.84
    whatever
    -1.82
     assurances
    -1.79
    DragonMagazine
    -1.79
    cott
    -1.78
     pronounce
    -1.77
     publications
    -1.76
    POSITIVE LOGITS
    apon
    2.22
     Functional
    1.92
    ォ
    1.88
     habitable
    1.86
    MRI
    1.81
     Aging
    1.77
     Habit
    1.76
    itudinal
    1.76
    visor
    1.75
    vironments
    1.74
    Activations Density 0.044%

    No Known Activations