© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 37578
    Prev
    Next
    INDEX
    Explanations

    elements related to visual and artistic attributes in various 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
    0:0.30
    1:0.07
    2:0.04
    3:0.04
    4:0.04
    5:0.12
    6:0.06
    7:0.01
    8:0.08
    9:0.07
    10:0.05
    11:0.04
    Negative Logits
     Panic
    -1.74
    abama
    -1.62
     Qué
    -1.57
     tremend
    -1.52
    ween
    -1.52
    racuse
    -1.50
     Hun
    -1.49
    ghai
    -1.46
     Taiwan
    -1.42
     fox
    -1.42
    POSITIVE LOGITS
    stals
    1.68
    Accessory
    1.57
    Layout
    1.53
    stones
    1.51
    suits
    1.50
    iatures
    1.49
    els
    1.47
    ettes
    1.46
    itars
    1.45
    sheets
    1.45
    Activations Density 0.217%

    No Known Activations