© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 15999
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to product development and engineering

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.05
    1:0.06
    2:0.10
    3:0.08
    4:0.06
    5:0.11
    6:0.05
    7:0.07
    8:0.10
    9:0.05
    10:0.14
    11:0.07
    Negative Logits
    BuyableInstoreAndOnline
    -1.45
     guiActiveUnfocused
    -1.29
     asylum
    -1.29
    Aid
    -1.27
     Arms
    -1.21
     Detail
    -1.21
     Proceed
    -1.18
     Forensic
    -1.16
     Advisory
    -1.12
     notoriety
    -1.12
    POSITIVE LOGITS
    said
    1.36
    vs
    1.25
     Sins
    1.25
     forgot
    1.24
    kind
    1.22
    uitive
    1.20
    insert
    1.19
    rists
    1.18
    }}}
    1.17
    ribes
    1.16
    Activations Density 0.097%

    No Known Activations