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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 3724
    Prev
    Next
    INDEX
    Explanations

    historical events and timelines

    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
    0:0.07
    1:0.03
    2:0.06
    3:0.11
    4:0.06
    5:0.09
    6:0.02
    7:0.17
    8:0.04
    9:0.02
    10:0.22
    11:0.06
    Negative Logits
    pport
    -2.51
    >>>
    -2.30
     selfies
    -2.29
     �
    -2.28
     selfie
    -2.21
    =#
    -2.17
     understands
    -2.13
    orry
    -2.12
     Yesterday
    -2.11
    know
    -2.11
    POSITIVE LOGITS
     eventually
    3.57
     thereafter
    3.52
     renamed
    3.34
    later
    3.34
     disbanded
    3.29
     later
    3.18
     subsequently
    3.09
     subsequent
    3.08
     1978
    3.03
     became
    3.01
    Activations Density 0.608%

    No Known Activations