© 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. 2-RES-JB
    11. 18643
    Prev
    Next
    INDEX
    Explanations

    comparisons or emphasis on higher quantities or degrees

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "more" indicating an increase or emphasis on quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xtap
    -0.72
     Classification
    -0.69
    MIT
    -0.66
    Enlarge
    -0.65
     Films
    -0.65
    OCK
    -0.64
    oresc
    -0.64
    oes
    -0.63
     Released
    -0.61
    Guard
    -0.60
    POSITIVE LOGITS
     than
    1.22
     stringent
    1.00
     sophisticated
    0.99
     expensive
    0.99
     ado
    0.96
     importantly
    0.95
     efficient
    0.94
     costly
    0.94
     manageable
    0.92
     complicated
    0.92
    Activations Density 0.162%

    No Known Activations