Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18611
    Prev
    Next
    INDEX
    Explanations

    references to names and events related to online posts or blogs

    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
    1:0.09
    2:0.04
    3:0.06
    4:0.05
    5:0.04
    6:0.05
    7:0.04
    8:0.03
    9:0.05
    10:0.08
    11:0.37
    Negative Logits
    %"
    -3.23
     \
    -3.17
    \<
    -2.90
    Enlarge
    -2.88
    %:
    -2.88
    «
    -2.88
    ■
    -2.77
     Might
    -2.74
     Of
    -2.70
    ..."
    -2.68
    POSITIVE LOGITS
    ublic
    2.27
    ashington
    2.18
     aboard
    2.17
    ishable
    2.17
     annot
    2.13
    oqu
    2.08
     pointing
    2.07
     dot
    2.06
     brace
    2.04
     individually
    2.03
    Activations Density 0.061%

    No Known Activations