© 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. 7-RES-JB
    11. 17257
    Prev
    Next
    INDEX
    Explanations

    examples or instances of a concept or idea

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating examples or instances of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ement
    -0.76
    izons
    -0.73
    ancies
    -0.73
     wig
    -0.69
    ossier
    -0.66
    LD
    -0.65
    ulum
    -0.65
     Debor
    -0.65
    iets
    -0.64
     Tours
    -0.64
    POSITIVE LOGITS
     collateral
    0.78
     fut
    0.76
     plagiar
    0.76
     unintended
    0.72
     guiActiveUnfocused
    0.72
     heroism
    0.71
     tropes
    0.70
     examples
    0.68
     pitfalls
    0.68
     redeem
    0.65
    Activations Density 0.094%

    No Known Activations