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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 28306
    Prev
    Next
    INDEX
    Explanations

    financial indicators related to market performance and currency fluctuations

    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
    2:0.06
    3:0.12
    4:0.06
    5:0.07
    6:0.02
    7:0.04
    8:0.05
    9:0.11
    10:0.18
    11:0.18
    Negative Logits
    thood
    -1.46
     sociop
    -1.21
     pedoph
    -1.12
     Mormons
    -1.12
     treasure
    -1.11
     shit
    -1.09
     adventures
    -1.07
     ensl
    -1.06
     glory
    -1.04
     fucking
    -1.04
    POSITIVE LOGITS
    Leaks
    1.10
     Thomson
    1.05
    heat
    1.04
    Focus
    1.04
    WASHINGTON
    1.03
    illon
    1.03
    tur
    1.03
    oglu
    1.01
     WATCHED
    1.01
    lde
    1.00
    Activations Density 0.508%

    No Known Activations