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. 5-ATT-KK
    6. 2777
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to genetics and genomics

    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
    0:0.02
    1:0.01
    2:0.15
    3:0.11
    4:0.08
    5:0.04
    6:0.03
    7:0.05
    8:0.07
    9:0.08
    10:0.18
    11:0.12
    Negative Logits
    Jimmy
    -1.25
    Trust
    -1.23
    Politics
    -1.22
    ACY
    -1.15
    bernatorial
    -1.14
    iversary
    -1.14
    olicy
    -1.14
    Honest
    -1.11
     Audit
    -1.11
    trust
    -1.11
    POSITIVE LOGITS
     ultraviolet
    1.38
     vanishing
    1.34
     clustered
    1.30
     coales
    1.24
     condu
    1.22
     pores
    1.22
     decom
    1.21
     dens
    1.19
     synthes
    1.18
     correspond
    1.18
    Activations Density 0.432%

    No Known Activations