© 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. 43609
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and dates related to significant events

    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
    0:0.04
    1:0.06
    2:0.08
    3:0.04
    4:0.03
    5:0.05
    6:0.40
    7:0.03
    8:0.03
    9:0.06
    10:0.07
    11:0.06
    Negative Logits
    acebook
    -1.61
     IMAGES
    -1.37
    soever
    -1.33
     secondly
    -1.32
    itiveness
    -1.32
     allowances
    -1.31
     stamps
    -1.24
    SHIP
    -1.24
     offerings
    -1.23
     staples
    -1.23
    POSITIVE LOGITS
    ahu
    1.68
    ober
    1.63
    ivo
    1.54
    aeda
    1.54
    arch
    1.46
    aghd
    1.46
    ouf
    1.45
    nih
    1.43
    fi
    1.43
    az
    1.42
    Activations Density 0.003%

    No Known Activations