© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 9497
    Prev
    Next
    INDEX
    Explanations

    financial or monetary terms related to costs and expenses

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of costs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unin
    -0.80
    mbuds
    -0.76
    IPS
    -0.72
    inton
    -0.70
    INTON
    -0.70
    gdala
    -0.70
    itialized
    -0.70
    buquerque
    -0.69
    ITAL
    -0.67
    ITNESS
    -0.66
    POSITIVE LOGITS
     incurred
    1.37
    umers
    1.00
     burden
    0.93
    umed
    0.91
     burdens
    0.87
     taxpayers
    0.86
     overrun
    0.85
     levied
    0.83
     associated
    0.83
     payable
    0.82
    Activations Density 0.025%

    No Known Activations