© 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. 42543
    Prev
    Next
    INDEX
    Explanations

    syntax-related errors in coding contexts

    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
    0:0.14
    1:0.28
    2:0.03
    3:0.03
    4:0.03
    5:0.22
    6:0.05
    7:0.01
    8:0.03
    9:0.06
    10:0.04
    11:0.02
    Negative Logits
     Helic
    -1.99
     Chau
    -1.92
     Kaf
    -1.87
     tet
    -1.87
     Leilan
    -1.86
     Tam
    -1.84
     Kag
    -1.82
     bot
    -1.81
     ham
    -1.81
     Elf
    -1.80
    POSITIVE LOGITS
    rating
    2.48
    aled
    2.45
    escription
    2.36
    atically
    2.24
    ordering
    2.22
    ends
    2.18
    alled
    2.18
    amen
    2.17
    alling
    2.16
    esses
    2.16
    Activations Density 0.065%

    No Known Activations