© 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. 4-RES-JB
    11. 10441
    Prev
    Next
    INDEX
    Explanations

    terms related to sustainability initiatives and environmental responsibility

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sustainability and environmental responsibility

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

    No Comments

    Negative Logits
    arius
    -0.84
    hner
    -0.77
    horn
    -0.77
    peak
    -0.75
    quist
    -0.75
    illary
    -0.73
    chu
    -0.72
    qt
    -0.71
    amen
    -0.70
    oan
    -0.70
    POSITIVE LOGITS
    ness
    0.98
     minded
    0.90
     environments
    0.90
     alternatives
    0.90
     spaces
    0.87
    NESS
    0.84
     environment
    0.83
     compact
    0.82
     ones
    0.82
     alternative
    0.82
    Activations Density 0.161%

    No Known Activations