© 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. 11-RES-JB
    11. 353
    Prev
    Next
    INDEX
    Explanations

    descriptions related to musical elements such as string instruments, melodies, basslines, percussion, and sound quality

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their associated sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     medicine
    -0.79
     confidentiality
    -0.72
     lawyers
    -0.72
     mail
    -0.71
     stuff
    -0.69
     biological
    -0.69
     guy
    -0.68
     people
    -0.67
     yell
    -0.67
     health
    -0.67
    POSITIVE LOGITS
     Whilst
    1.40
    Yet
    1.35
     Nonetheless
    1.31
    Indeed
    1.29
    Nevertheless
    1.29
    Amid
    1.27
     Nevertheless
    1.27
    Despite
    1.25
    Though
    1.24
    Upon
    1.21
    Activations Density 0.539%

    No Known Activations