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. 5-ATT-KK
    6. 7074
    Prev
    Next
    INDEX
    Explanations

    references to ongoing investigations and their associated parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.16
    3:0.15
    4:0.29
    5:0.03
    6:0.03
    7:0.10
    8:0.04
    9:0.03
    10:0.04
    11:0.05
    Negative Logits
    retty
    -1.38
     inexper
    -1.38
     mitigating
    -1.37
    ��
    -1.34
     reassured
    -1.34
    autions
    -1.32
    imposed
    -1.32
    regon
    -1.28
    0000000
    -1.27
     lengths
    -1.26
    POSITIVE LOGITS
    ghazi
    1.59
    acas
    1.47
     viz
    1.45
     Sap
    1.44
     Revolution
    1.37
     Arg
    1.34
     da
    1.33
    ogenesis
    1.32
     Fell
    1.32
    opolis
    1.31
    Activations Density 0.419%

    No Known Activations