© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 42766
    Prev
    Next
    INDEX
    Explanations

    references to technology and devices, particularly related to digital tools for organization

    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
    0:0.01
    1:0.01
    2:0.24
    3:0.26
    4:0.08
    5:0.04
    6:0.03
    7:0.04
    8:0.04
    9:0.06
    10:0.08
    11:0.05
    Negative Logits
     antid
    -1.51
     Hath
    -1.50
     Schne
    -1.45
     Lauder
    -1.39
     superiors
    -1.38
     Universities
    -1.37
     Newsp
    -1.35
     subcommittee
    -1.34
     Interior
    -1.32
     shareholder
    -1.32
    POSITIVE LOGITS
     avg
    1.80
    !!!!
    1.71
     captcha
    1.69
     david
    1.66
    !!!!!
    1.64
    arez
    1.64
    channelAvailability
    1.59
     ·
    1.59
     img
    1.58
     sd
    1.58
    Activations Density 0.005%

    No Known Activations