© 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. 46224
    Prev
    Next
    INDEX
    Explanations

    the word "for" and related prepositions indicating purpose or reasons

    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
    1:0.01
    2:0.08
    3:0.07
    4:0.09
    5:0.04
    6:0.07
    7:0.22
    8:0.04
    9:0.04
    10:0.06
    11:0.19
    Negative Logits
     Nights
    -1.86
    modules
    -1.68
    ebook
    -1.67
     Wyn
    -1.63
    acqu
    -1.55
    GPU
    -1.54
    ��極
    -1.53
    average
    -1.53
    worldly
    -1.53
     bounces
    -1.52
    POSITIVE LOGITS
     harm
    1.80
     coercion
    1.75
     dissenting
    1.74
     tampering
    1.66
     dissent
    1.55
     disagreement
    1.55
    ongyang
    1.55
     compromise
    1.54
     intervention
    1.52
     substitution
    1.50
    Activations Density 0.001%

    No Known Activations