© 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. 2-RES-JB
    11. 9053
    Prev
    Next
    INDEX
    Explanations

    colors and color combinations in text

    oai_token-act-pair · gpt-3.5-turbo

    references to various colors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    minist
    -0.78
    aton
    -0.77
     privat
    -0.71
    lease
    -0.69
     guiActiveUn
    -0.68
    idable
    -0.68
    adle
    -0.68
    mun
    -0.68
    agra
    -0.66
    EH
    -0.65
    POSITIVE LOGITS
    ish
    0.86
     oval
    0.72
    dimension
    0.72
     rectangular
    0.70
     ones
    0.69
     deviation
    0.65
    ness
    0.65
     equivalents
    0.64
     heterogeneity
    0.63
     flakes
    0.63
    Activations Density 0.232%

    No Known Activations