© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 46510
    Prev
    Next
    INDEX
    Explanations

    prepositions 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
    0:0.03
    1:0.02
    2:0.10
    3:0.08
    4:0.11
    5:0.04
    6:0.03
    7:0.30
    8:0.03
    9:0.04
    10:0.13
    11:0.06
    Negative Logits
    shadow
    -1.75
    ��
    -1.67
    ��
    -1.61
     largeDownload
    -1.58
    IFA
    -1.53
    elli
    -1.52
    Justice
    -1.51
    ��
    -1.51
    acio
    -1.50
    redo
    -1.49
    POSITIVE LOGITS
     ranges
    1.55
    aband
    1.50
     Veh
    1.46
     poisoning
    1.44
     intox
    1.43
     tested
    1.41
     Kraken
    1.41
     commercially
    1.41
     quantities
    1.40
    bsite
    1.40
    Activations Density 0.000%

    No Known Activations