© 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. 8-RES-JB
    11. 15026
    Prev
    Next
    INDEX
    Explanations

    colors and color-related terms in the document

    oai_token-act-pair · gpt-3.5-turbo

    colors and their combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utics
    -0.79
    ertodd
    -0.75
     Rica
    -0.71
    chwitz
    -0.68
    dain
    -0.64
     Posted
    -0.64
    ASHINGTON
    -0.63
    HCR
    -0.61
    olia
    -0.61
    aukee
    -0.61
    POSITIVE LOGITS
     portion
    1.09
    iest
    1.05
     version
    1.03
     ones
    1.02
     aspect
    1.00
     element
    0.94
    liest
    0.92
     equivalents
    0.90
     counterpart
    0.89
     equivalent
    0.89
    Activations Density 0.731%

    No Known Activations