© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 19436
    Prev
    Next
    INDEX
    Explanations

    keywords associated with significant size or importance

    oai_token-act-pair · gpt-3.5-turbo

    the term "huge" and its contextual usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nery
    -0.83
    manship
    -0.83
    Reviewed
    -0.82
    ices
    -0.80
    istry
    -0.78
    gemony
    -0.78
    cling
    -0.78
    former
    -0.76
    pai
    -0.76
    qi
    -0.73
    POSITIVE LOGITS
     amounts
    1.14
     amount
    0.97
     quantities
    0.95
     chunks
    0.93
     swath
    0.93
     leaps
    0.91
     sums
    0.88
     chunk
    0.87
     disparity
    0.85
     swat
    0.85
    Activations Density 0.054%

    No Known Activations