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. 18775
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    0:0.09
    1:0.07
    2:0.07
    3:0.09
    4:0.08
    5:0.08
    6:0.08
    7:0.08
    8:0.07
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
    ��
    -3.04
     Thorn
    -2.71
    bits
    -2.67
    Rust
    -2.65
     creep
    -2.63
    dy
    -2.61
    rawdownloadcloneembedreportprint
    -2.55
     Melt
    -2.55
    ────────
    -2.54
     Bloom
    -2.48
    POSITIVE LOGITS
    oqu
    3.14
    tarian
    2.83
    ourses
    2.70
     GPA
    2.52
     pronoun
    2.50
     CSV
    2.43
    arag
    2.42
     OU
    2.42
     pronouns
    2.40
    asury
    2.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.