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. 7039
    Prev
    Next
    INDEX
    Explanations

    elements indicating organization and planning in various contexts

    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
    0:0.16
    1:0.04
    2:0.07
    3:0.08
    4:0.08
    5:0.13
    6:0.04
    7:0.03
    8:0.21
    9:0.03
    10:0.05
    11:0.04
    Negative Logits
     Motion
    -1.59
    iannopoulos
    -1.58
    Motion
    -1.55
     Classification
    -1.43
     702
    -1.42
     rall
    -1.41
     Lyons
    -1.41
    Stat
    -1.40
     Christensen
    -1.40
    emporary
    -1.39
    POSITIVE LOGITS
    ................
    2.48
    ........................
    2.45
    ...?
    2.37
    ........
    2.32
    ......
    2.23
    ...)
    2.11
    .......
    2.05
    .....
    2.02
    !!!!
    2.02
    .........
    1.97
    Activations Density 0.004%

    No Known Activations