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. 5-ATT-KK
    6. 3070
    Prev
    Next
    INDEX
    Explanations

    statements expressing personal beliefs or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.11
    3:0.17
    4:0.13
    5:0.03
    6:0.07
    7:0.13
    8:0.05
    9:0.05
    10:0.05
    11:0.11
    Negative Logits
    ゴン
    -1.76
     beware
    -1.40
     presumably
    -1.36
    911
    -1.35
    along
    -1.30
    onomy
    -1.26
    arc
    -1.26
     Resp
    -1.26
     Tud
    -1.26
    unknown
    -1.24
    POSITIVE LOGITS
     Flavoring
    2.39
     nor
    1.83
     anymore
    1.57
    illard
    1.42
     conclusive
    1.37
    icans
    1.34
     filibuster
    1.31
     ANY
    1.27
    icer
    1.26
    orgetown
    1.26
    Activations Density 0.014%

    No Known Activations