© 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. 1-RES-JB
    11. 20977
    Prev
    Next
    INDEX
    Explanations

    adjectives comparing two things, specifically focusing on the word "more."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "more" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xtap
    -0.69
     Classification
    -0.68
    oes
    -0.67
    Enlarge
    -0.66
    oresc
    -0.65
    ress
    -0.62
    nikov
    -0.62
    ital
    -0.62
     Released
    -0.62
    Guard
    -0.61
    POSITIVE LOGITS
     than
    1.11
     sophisticated
    0.95
     stringent
    0.95
     importantly
    0.93
     ado
    0.93
     complicated
    0.90
     costly
    0.89
     expensive
    0.89
     efficient
    0.88
     elaborate
    0.86
    Activations Density 0.130%

    No Known Activations