© 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. 28065
    Prev
    Next
    INDEX
    Explanations

    references to locations, particularly in relation to people and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    1:0.01
    2:0.05
    3:0.06
    4:0.14
    5:0.12
    6:0.04
    7:0.09
    8:0.11
    9:0.05
    10:0.19
    11:0.07
    Negative Logits
    20439
    -2.59
    acter
    -2.04
    rencies
    -1.84
    irit
    -1.80
    CLAIM
    -1.80
    gey
    -1.78
    arget
    -1.77
    ailed
    -1.75
    xon
    -1.73
    agher
    -1.70
    POSITIVE LOGITS
     Cathedral
    1.92
     town
    1.84
     vacant
    1.79
     walls
    1.78
    ropolis
    1.78
    atown
    1.76
     Chinatown
    1.73
     sew
    1.72
    wide
    1.72
     nicer
    1.71
    Activations Density 0.024%

    No Known Activations