Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10572
    Prev
    Next
    INDEX
    Explanations

    philosophical quotes and reflections on self-improvement

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and formatting symbols

    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
     accrued
    -0.84
     mounted
    -0.80
     combined
    -0.79
     overshadow
    -0.79
    otin
    -0.76
     thwarted
    -0.76
     accumulated
    -0.76
     permits
    -0.76
     prepar
    -0.75
     protective
    -0.75
    POSITIVE LOGITS
    Anonymous
    1.48
    Eric
    1.27
    Christopher
    1.26
    Dave
    1.25
    Henry
    1.24
    George
    1.24
    David
    1.24
    Thomas
    1.24
    Nick
    1.24
    Edward
    1.23
    Activations Density 0.092%

    No Known Activations