© 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. 41730
    Prev
    Next
    INDEX
    Explanations

    proper names and titles of people in the context of advocacy and governance

    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
    1:0.03
    2:0.08
    3:0.13
    4:0.27
    5:0.05
    6:0.04
    7:0.04
    8:0.05
    9:0.06
    10:0.12
    11:0.05
    Negative Logits
    anship
    -1.70
     awa
    -1.65
     ONLY
    -1.54
    erate
    -1.46
    etheless
    -1.44
    peat
    -1.43
     proper
    -1.43
     */
    -1.42
     rigged
    -1.41
    cessive
    -1.40
    POSITIVE LOGITS
    said
    2.11
     said
    2.01
     says
    1.98
     exclaimed
    1.68
    told
    1.63
     explains
    1.63
     quoted
    1.61
    ivan
    1.60
     lamented
    1.59
     wrote
    1.56
    Activations Density 0.109%

    No Known Activations