© 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. 0-RES-JB
    11. 8399
    Prev
    Next
    INDEX
    Explanations

    polymers and materials related to waterproofing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to synthetic materials and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atto
    -0.80
     MacArthur
    -0.74
    ¥µ
    -0.74
    ĨĴ
    -0.73
    =-=-=-=-=-=-=-=-
    -0.72
    Swe
    -0.72
    lda
    -0.72
    osen
    -0.71
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.70
    \\\\\\\\
    -0.70
    POSITIVE LOGITS
     polymer
    2.40
     nylon
    1.43
     resin
    0.89
    raft
    0.82
     waterproof
    0.78
     textile
    0.77
    mers
    0.75
     ..."
    0.73
    Material
    0.73
     acrylic
    0.72
    Activations Density 0.011%

    No Known Activations