© 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. 3-ATT-KK
    11. 8113
    Prev
    Next
    INDEX
    Explanations

    references to identity and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.05
    2:0.10
    3:0.04
    4:0.03
    5:0.08
    6:0.14
    7:0.09
    8:0.12
    9:0.07
    10:0.09
    11:0.12
    Negative Logits
    士
    -1.24
    poke
    -1.23
     theirs
    -1.05
    ently
    -1.02
     outweigh
    -1.01
     Javascript
    -0.96
    eers
    -0.96
    reads
    -0.95
    untarily
    -0.93
    reply
    -0.93
    POSITIVE LOGITS
    Sym
    1.19
    MSN
    1.08
    UC
    1.01
    scl
    1.01
    isphere
    0.99
    oqu
    0.98
     Osw
    0.96
     appell
    0.96
     Sym
    0.94
    onne
    0.93
    Activations Density 0.018%

    No Known Activations