© 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. 6-RES-JB
    11. 13517
    Prev
    Next
    INDEX
    Explanations

    phrases with a sense of multitude or abundance

    oai_token-act-pair · gpt-3.5-turbo

    the word "numerous" to indicate frequency or abundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atum
    -0.82
    fter
    -0.72
    ocene
    -0.71
    ema
    -0.68
    heed
    -0.68
    emb
    -0.68
    hop
    -0.68
    iman
    -0.67
    istan
    -0.67
    ender
    -0.66
    POSITIVE LOGITS
     occasions
    1.04
     iterations
    0.99
     instances
    0.92
     facets
    0.92
     occurrences
    0.91
     unanswered
    0.87
     ways
    0.86
     rounds
    0.86
     times
    0.85
     aspects
    0.82
    Activations Density 0.023%

    No Known Activations