© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17120
    Prev
    Next
    INDEX
    Explanations

    words related to the energy sector, such as "Energy," "Department of Energy," and "Regulatory Commission."

    oai_token-act-pair · gpt-3.5-turbo

    references to energy-related topics and organizations

    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
    enance
    -0.94
    glers
    -0.94
    lihood
    -0.80
    gery
    -0.80
    geries
    -0.79
    atar
    -0.74
    ãĥīãĥ©
    -0.73
    allery
    -0.73
    ifier
    -0.72
    ARDIS
    -0.72
    POSITIVE LOGITS
     Enhancement
    0.82
     propulsion
    0.76
    minist
    0.74
     Regulatory
    0.73
     Ranger
    0.69
     powering
    0.68
     Efficiency
    0.67
     Supply
    0.67
     Sciences
    0.66
     insulation
    0.65
    Activations Density 0.023%

    No Known Activations