© 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. 41599
    Prev
    Next
    INDEX
    Explanations

    references to architectural features or components

    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
    0:0.03
    1:0.02
    2:0.12
    3:0.06
    4:0.09
    5:0.05
    6:0.06
    7:0.20
    8:0.03
    9:0.03
    10:0.10
    11:0.17
    Negative Logits
    fixes
    -1.39
     guiActiveUnfocused
    -1.35
    ◼
    -1.26
    prints
    -1.25
    binding
    -1.25
     Symptoms
    -1.24
     Fixes
    -1.19
     identifiers
    -1.19
    ibrary
    -1.19
    bugs
    -1.18
    POSITIVE LOGITS
    izon
    1.22
     terminated
    1.20
     undercover
    1.18
     questioned
    1.17
     mature
    1.13
     capped
    1.12
     matured
    1.12
     polic
    1.08
    poke
    1.07
     interrogated
    1.07
    Activations Density 0.029%

    No Known Activations