© 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. 10-ATT-KK
    11. 12412
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.02
    2:0.02
    3:0.03
    4:0.05
    5:0.30
    6:0.02
    7:0.03
    8:0.02
    9:0.36
    10:0.02
    11:0.04
    Negative Logits
     denouncing
    -2.93
     stating
    -2.92
     dismissing
    -2.90
    ouncing
    -2.81
    angering
    -2.72
    asuring
    -2.71
     rejecting
    -2.66
     indicating
    -2.65
     admitting
    -2.60
     citing
    -2.56
    POSITIVE LOGITS
     helps
    4.16
     solves
    3.97
     isn
    3.90
    helps
    3.84
     improves
    3.65
     sucks
    3.65
     requires
    3.58
     doesn
    3.53
     brings
    3.49
     strengthens
    3.48
    Activations Density 0.281%

    No Known Activations