© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 16952
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or decisions made at the expense of something or someone else

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference the concept of "expense" in relation to various subjects and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odes
    -0.91
    nai
    -0.79
    DIT
    -0.75
    lining
    -0.72
    jong
    -0.72
    erk
    -0.72
    unin
    -0.71
    mbuds
    -0.71
    kens
    -0.70
     Aval
    -0.68
    POSITIVE LOGITS
     incurred
    1.02
     expense
    0.99
     spared
    0.90
    folios
    0.78
    ãĥĨãĤ£
    0.77
     reimbursement
    0.75
     expenditure
    0.75
    itures
    0.75
     reimburse
    0.74
    umed
    0.73
    Activations Density 0.008%

    No Known Activations