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

    Neuronpedia

    APICircuit 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. 20713
    Prev
    Next
    INDEX
    Explanations

    keywords related to support and significance in a context

    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
    0:0.08
    1:0.09
    2:0.08
    3:0.08
    4:0.07
    5:0.09
    6:0.07
    7:0.07
    8:0.08
    9:0.09
    10:0.08
    11:0.07
    Negative Logits
    idia
    -3.55
    etsk
    -3.26
    Downloadha
    -3.14
    Naz
    -2.92
    idium
    -2.87
    Nik
    -2.72
     coron
    -2.70
    iku
    -2.68
     tripod
    -2.62
    idav
    -2.61
    POSITIVE LOGITS
    oğ
    2.77
     DIRECT
    2.61
    、
    2.61
     Designer
    2.59
     TTL
    2.50
     RELE
    2.45
     Waters
    2.44
    ット
    2.41
     FUN
    2.40
     Loop
    2.39
    Activations Density 0.000%

    No Known Activations