© 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 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. 8921
    Prev
    Next
    INDEX
    Explanations

    dates and specific references to time

    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
    0:0.03
    1:0.10
    2:0.03
    3:0.08
    4:0.02
    5:0.11
    6:0.02
    7:0.09
    8:0.02
    9:0.08
    10:0.03
    11:0.33
    Negative Logits
     symp
    -2.24
    .]
    -2.24
    :{
    -2.12
    .}
    -2.08
    acl
    -2.06
     handling
    -2.04
    PUT
    -2.01
     conce
    -2.00
    iqueness
    -1.99
    EStreamFrame
    -1.96
    POSITIVE LOGITS
     29
    2.69
     23
    2.67
     28
    2.63
     22
    2.57
     33
    2.54
     27
    2.44
     284
    2.40
     303
    2.36
     293
    2.36
     283
    2.36
    Activations Density 0.008%

    No Known Activations