© 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. 5-ATT-KK
    11. 26788
    Prev
    Next
    INDEX
    Explanations

    variations of the letter 'l' in different contexts

    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
    2:0.12
    3:0.04
    4:0.03
    5:0.04
    6:0.35
    7:0.03
    8:0.06
    9:0.06
    10:0.08
    11:0.05
    Negative Logits
     bun
    -1.29
     gre
    -1.16
     condem
    -1.09
     envelop
    -1.07
     sil
    -1.06
    stadt
    -1.05
     coli
    -1.05
     uncond
    -1.04
     Hann
    -1.02
     loaf
    -1.02
    POSITIVE LOGITS
    ️
    1.81
    actionDate
    1.67
    odox
    1.56
     Marketable
    1.54
    emort
    1.45
    actual
    1.41
    minus
    1.37
    henko
    1.37
    inarily
    1.36
    ateral
    1.32
    Activations Density 0.164%

    No Known Activations