© 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. 2854
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "To put it" or variations of this phrase

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express simplification or clarification of complex ideas

    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
    iller
    -0.67
    jar
    -0.65
    iership
    -0.65
     unfocusedRange
    -0.64
    externalActionCode
    -0.62
    ordial
    -0.61
    anded
    -0.60
    assic
    -0.60
    bies
    -0.60
    available
    -0.58
    POSITIVE LOGITS
     aside
    1.01
     bluntly
    0.92
     succinct
    0.81
     plainly
    0.77
    hetically
    0.77
    itud
    0.75
    atively
    0.75
     together
    0.71
    ently
    0.70
    ogether
    0.67
    Activations Density 0.038%

    No Known Activations