© 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. 20342
    Prev
    Next
    INDEX
    Explanations

    titles, references, and formal addresses related to notable individuals

    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
    0:0.03
    1:0.03
    2:0.07
    3:0.07
    4:0.09
    5:0.03
    6:0.14
    7:0.23
    8:0.03
    9:0.05
    10:0.13
    11:0.05
    Negative Logits
    etti
    -1.79
    eor
    -1.71
    ivo
    -1.69
    oter
    -1.66
    eton
    -1.65
    leck
    -1.61
    illac
    -1.58
    ively
    -1.56
    otin
    -1.55
    roots
    -1.55
    POSITIVE LOGITS
    Discussion
    1.63
    Haw
    1.51
     Asked
    1.50
    FAQ
    1.50
    Secret
    1.46
     Gifts
    1.46
    Republic
    1.45
     Conversation
    1.44
    Hey
    1.44
    IRED
    1.43
    Activations Density 0.000%

    No Known Activations