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. 11425
    Prev
    Next
    INDEX
    Explanations

    topics related to technology and governance

    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
    1:0.02
    2:0.03
    3:0.22
    4:0.04
    5:0.07
    6:0.02
    7:0.06
    8:0.03
    9:0.03
    10:0.37
    11:0.03
    Negative Logits
     ));
    -2.51
    ��
    -2.19
    OULD
    -2.15
    pires
    -2.14
    usually
    -2.10
    ));
    -2.07
    udeb
    -1.98
     slightest
    -1.95
    ��
    -1.94
    )),
    -1.92
    POSITIVE LOGITS
     history
    2.64
     culminating
    2.47
     developments
    2.37
     detailing
    2.34
     unfolding
    2.26
    comings
    2.22
     Timeline
    2.21
     revealing
    2.15
     journey
    2.15
     fascinating
    2.15
    Activations Density 0.399%

    No Known Activations