© 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. 43373
    Prev
    Next
    INDEX
    Explanations

    indicators of emphasis or important points in the text

    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
    2:0.06
    3:0.08
    4:0.04
    5:0.04
    6:0.14
    7:0.02
    8:0.05
    9:0.05
    10:0.17
    11:0.24
    Negative Logits
    vals
    -1.61
    adjust
    -1.59
     accuracy
    -1.54
    LOD
    -1.53
     Quadro
    -1.48
     triangles
    -1.47
     bounds
    -1.43
    ternity
    -1.40
    entity
    -1.33
     approximation
    -1.32
    POSITIVE LOGITS
    etsk
    1.81
    oyer
    1.60
     )]
    1.57
    ublic
    1.51
    cong
    1.51
    .")
    1.47
    opian
    1.46
     atmosphere
    1.45
     Belg
    1.44
    ]."
    1.43
    Activations Density 0.001%

    No Known Activations