© 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. 40817
    Prev
    Next
    INDEX
    Explanations

    instances of the word "with" and its variations, indicating conditions or qualifications in statements

    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
    0:0.02
    1:0.02
    2:0.08
    3:0.04
    4:0.07
    5:0.04
    6:0.04
    7:0.49
    8:0.02
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
    acio
    -1.81
    pter
    -1.78
    uart
    -1.74
    igree
    -1.74
    ftime
    -1.72
    Downloadha
    -1.72
    fman
    -1.72
    arta
    -1.71
    rame
    -1.70
    esse
    -1.66
    POSITIVE LOGITS
     PID
    1.58
     admitting
    1.57
     piracy
    1.55
     dissenting
    1.55
     financially
    1.54
     granting
    1.53
     sharing
    1.53
     disagree
    1.52
     lett
    1.52
     dissent
    1.50
    Activations Density 0.003%

    No Known Activations