© 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. 10539
    Prev
    Next
    INDEX
    Explanations

    specific measurements and technical details, particularly related to weights and dimensions

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and specifications related to measurements and performance

    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
    product
    -0.71
    unction
    -0.68
    ĪĴ
    -0.64
    mone
    -0.63
    idden
    -0.61
    products
    -0.61
    otin
    -0.59
    iership
    -0.59
    vell
    -0.57
    rance
    -0.57
    POSITIVE LOGITS
     varies
    1.26
     ranged
    0.92
    :
    0.91
     vary
    0.87
     Approximately
    0.86
     depends
    0.86
    :'
    0.86
     TBD
    0.85
     =
    0.84
     Unknown
    0.84
    Activations Density 0.181%

    No Known Activations