© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 37096
    Prev
    Next
    INDEX
    Explanations

    terms related to geological processes and rock types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.06
    1:0.01
    2:0.09
    3:0.10
    4:0.07
    5:0.05
    6:0.02
    7:0.07
    8:0.07
    9:0.08
    10:0.20
    11:0.14
    Negative Logits
    natureconservancy
    -1.29
     controversy
    -1.26
     controversies
    -1.21
     Pulitzer
    -1.16
    review
    -1.13
    adem
    -1.13
     Trends
    -1.12
     Reasons
    -1.11
     censorship
    -1.11
     finalists
    -1.09
    POSITIVE LOGITS
     transmitted
    1.41
    NetMessage
    1.40
     deposits
    1.35
     gases
    1.30
     depos
    1.27
    cium
    1.25
     downstream
    1.24
    rients
    1.23
     deposited
    1.22
     molecules
    1.21
    Activations Density 0.388%

    No Known Activations