© 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. 40841
    Prev
    Next
    INDEX
    Explanations

    references to significant events or milestones in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.02
    2:0.16
    3:0.07
    4:0.06
    5:0.06
    6:0.05
    7:0.07
    8:0.03
    9:0.04
    10:0.10
    11:0.27
    Negative Logits
    idae
    -2.13
    abre
    -2.08
    nown
    -2.04
    vae
    -1.95
    bugs
    -1.95
    bug
    -1.91
    atically
    -1.88
    ????????
    -1.79
     Hebdo
    -1.78
     prank
    -1.77
    POSITIVE LOGITS
     Mortgage
    1.94
    taboola
    1.81
     housing
    1.78
     Occupations
    1.76
     currencies
    1.75
    soDeliveryDate
    1.75
     Mn
    1.73
     Wage
    1.73
     borrowers
    1.71
     Pillar
    1.70
    Activations Density 0.000%

    No Known Activations