© 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. 9615
    Prev
    Next
    INDEX
    Explanations

    references to news sources and imagery related to events

    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
    0:0.05
    1:0.03
    2:0.03
    3:0.05
    4:0.10
    5:0.15
    6:0.03
    7:0.30
    8:0.07
    9:0.03
    10:0.07
    11:0.03
    Negative Logits
    url
    -2.53
    semble
    -2.51
    nis
    -2.39
    rel
    -2.32
    rev
    -2.30
    ric
    -2.23
    onte
    -2.16
    REL
    -2.14
    ril
    -2.14
    lies
    -2.12
    POSITIVE LOGITS
    NetMessage
    2.60
     Donation
    2.54
     Ending
    2.33
    Abstract
    2.33
     enriched
    2.26
     Feedback
    2.16
    anasia
    2.16
     Actions
    2.12
     External
    2.10
    Third
    2.07
    Activations Density 0.005%

    No Known Activations