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. 44
    Prev
    Next
    INDEX
    Explanations

    references to mountain gorillas and related themes

    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
    0:0.04
    1:0.04
    2:0.04
    3:0.11
    4:0.08
    5:0.14
    6:0.05
    7:0.21
    8:0.03
    9:0.05
    10:0.06
    11:0.08
    Negative Logits
     ende
    -2.96
     compr
    -2.94
     commer
    -2.88
     desper
    -2.80
     appre
    -2.72
    ``
    -2.68
    �
    -2.58
     eleph
    -2.58
     arrang
    -2.55
     produ
    -2.54
    POSITIVE LOGITS
     Vatican
    2.57
     Campbell
    2.45
    bourg
    2.31
    atican
    2.28
     Ont
    2.26
    USS
    2.24
    minster
    2.23
    mony
    2.22
     –
    2.21
    ophers
    2.17
    Activations Density 0.001%

    No Known Activations