© 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. 7-RES-JB
    11. 7318
    Prev
    Next
    INDEX
    Explanations

    references to objects related to plumbing or pipes

    oai_token-act-pair · gpt-3.5-turbo
    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
    enance
    -0.88
    ERAL
    -0.77
    é¾įå
    -0.75
    eanor
    -0.75
    ean
    -0.74
    doms
    -0.73
    apego
    -0.71
    ãħĭ
    -0.71
    nesota
    -0.71
    neapolis
    -0.70
    POSITIVE LOGITS
    pipe
    1.07
     cleaners
    1.02
     pipe
    0.98
     pipes
    0.92
     Pipe
    0.87
     cleaner
    0.84
     piping
    0.81
    fit
    0.77
    cone
    0.75
    bley
    0.74
    Activations Density 0.016%

    No Known Activations