© 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 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. 9-RES-JB
    11. 18282
    Prev
    Next
    INDEX
    Explanations

    words related to various actions involving the disposal and reuse of items, particularly recycling

    oai_token-act-pair · gpt-3.5-turbo

    terms related to recycling and waste management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    htar
    -0.77
    ority
    -0.76
    insula
    -0.76
    witz
    -0.71
    ellen
    -0.68
    inen
    -0.68
    andr
    -0.67
    mpeg
    -0.66
    zai
    -0.65
    quart
    -0.65
    POSITIVE LOGITS
     bins
    1.13
     recycle
    1.07
     recy
    1.03
     recycling
    0.96
     recycled
    0.93
    ycle
    0.91
     Waste
    0.89
     wastewater
    0.86
     cans
    0.85
    ibles
    0.82
    Activations Density 0.060%

    No Known Activations