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. 11295
    Prev
    Next
    INDEX
    Explanations

    numerical data related to financial commitments

    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
    0:0.03
    1:0.41
    2:0.03
    3:0.08
    4:0.03
    5:0.06
    6:0.05
    7:0.06
    8:0.03
    9:0.08
    10:0.04
    11:0.05
    Negative Logits
     lowly
    -2.79
     1987
    -2.52
     solitude
    -2.52
    amera
    -2.51
     shameless
    -2.50
    chant
    -2.43
    nikov
    -2.36
     ordinary
    -2.34
     1983
    -2.33
     indign
    -2.30
    POSITIVE LOGITS
     2019
    5.62
     2018
    5.04
    2019
    4.86
    2018
    4.69
     2021
    4.59
    2020
    4.50
     2020
    4.45
     2022
    4.37
     2024
    4.28
     2025
    3.86
    Activations Density 0.019%

    No Known Activations