© 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. 3-RES-JB
    11. 9018
    Prev
    Next
    INDEX
    Explanations

    words related to colors

    oai_token-act-pair · gpt-3.5-turbo

    words related to colors and shades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thodox
    -0.86
    lessly
    -0.77
     accomplished
    -0.70
    ISC
    -0.70
    utherford
    -0.69
     infringing
    -0.66
    ILY
    -0.65
    yright
    -0.64
    real
    -0.62
    Sources
    -0.62
    POSITIVE LOGITS
    ige
    1.14
    emo
    0.85
    uner
    0.76
    emen
    0.76
    ues
    0.74
    baum
    0.74
    entials
    0.73
    hiro
    0.73
    ge
    0.70
    orge
    0.69
    Activations Density 0.010%

    No Known Activations