© 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. 41581
    Prev
    Next
    INDEX
    Explanations

    phrases related to parts of a whole or segmented structures

    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
    1:0.01
    2:0.11
    3:0.04
    4:0.19
    5:0.02
    6:0.08
    7:0.26
    8:0.02
    9:0.02
    10:0.05
    11:0.13
    Negative Logits
    76561
    -1.57
    erity
    -1.44
    ukong
    -1.26
     john
    -1.24
    fur
    -1.21
    fficiency
    -1.20
    urred
    -1.17
     doubted
    -1.16
    nsics
    -1.15
    acs
    -1.15
    POSITIVE LOGITS
     FIR
    1.35
     Category
    1.32
     MV
    1.30
    Category
    1.28
    Org
    1.27
    SPEC
    1.26
     continuum
    1.25
     proceedings
    1.23
     category
    1.23
    Zone
    1.21
    Activations Density 0.036%

    No Known Activations