© 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. 10-RES-JB
    11. 10133
    Prev
    Next
    INDEX
    Explanations

    numerical values such as quantities, statistics, and measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to demographics and health statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    danger
    -0.71
    redo
    -0.70
     Nib
    -0.69
    inventoryQuantity
    -0.67
    Tro
    -0.67
    Nonetheless
    -0.66
    )}
    -0.65
    pload
    -0.65
     workaround
    -0.65
    Nevertheless
    -0.64
    POSITIVE LOGITS
     sampled
    1.11
     spanning
    1.01
     randomly
    1.00
     conducted
    0.98
     surveyed
    0.97
     randomized
    0.94
     aged
    0.94
     interviewing
    0.92
     analyzed
    0.89
     anonymously
    0.89
    Activations Density 0.320%

    No Known Activations