© 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. 2603
    Prev
    Next
    INDEX
    Explanations

    references to people or entities named "Marcol"

    oai_token-act-pair · gpt-3.5-turbo

    references to the color "color" and its various usages or contexts in text

    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
     slack
    -0.72
     Rescue
    -0.71
     Kobe
    -0.65
     blame
    -0.64
     bite
    -0.63
     SLI
    -0.62
     whisper
    -0.61
     rescue
    -0.61
     ransom
    -0.61
    atsu
    -0.61
    POSITIVE LOGITS
    col
    4.39
    COL
    2.23
    Col
    2.02
    colour
    1.66
     Col
    1.52
    colored
    1.51
     col
    1.46
     COL
    1.42
    color
    1.32
    icol
    1.27
    Activations Density 0.005%

    No Known Activations