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. 7-ATT-KK
    6. 9061
    Prev
    Next
    INDEX
    Explanations

    references to legal and constitutional documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.15
    1:0.04
    2:0.01
    3:0.13
    4:0.29
    5:0.08
    6:0.05
    7:0.01
    8:0.11
    9:0.05
    10:0.01
    11:0.02
    Negative Logits
     Saiyan
    -2.22
    itudes
    -2.02
    actionDate
    -1.98
     alike
    -1.96
    artifacts
    -1.91
    itude
    -1.89
    %%%%
    -1.85
    unit
    -1.83
    isSpecialOrderable
    -1.82
    rely
    -1.82
    POSITIVE LOGITS
     Chambers
    2.00
     whereby
    1.89
     oun
    1.86
     teasp
    1.81
     clause
    1.77
     Clause
    1.72
     defence
    1.71
    aque
    1.66
    oked
    1.65
     prohibiting
    1.60
    Activations Density 0.003%

    No Known Activations