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. 10779
    Prev
    Next
    INDEX
    Explanations

    references to research papers and academic citations

    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
    0:0.14
    1:0.03
    2:0.03
    3:0.15
    4:0.03
    5:0.05
    6:0.04
    7:0.05
    8:0.06
    9:0.03
    10:0.27
    11:0.06
    Negative Logits
     authentic
    -2.05
     Liter
    -2.01
     Tycoon
    -1.94
     Identity
    -1.94
     Escape
    -1.93
    artisan
    -1.90
    akespeare
    -1.82
    igrant
    -1.81
    enic
    -1.81
     Bridge
    -1.76
    POSITIVE LOGITS
    ovember
    3.02
     Pt
    2.49
    )",
    2.34
     suppl
    2.33
     apr
    2.28
    ⓘ
    2.27
     DOI
    2.24
    cember
    2.23
    elight
    2.22
    rm
    2.21
    Activations Density 0.004%

    No Known Activations