© 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. 10098
    Prev
    Next
    INDEX
    Explanations

    phrases related to business activities and transactions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to agreements, policies, or structured systems

    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
     oneself
    -0.83
    ometric
    -0.73
    cair
    -0.68
    otropic
    -0.68
    illian
    -0.61
    Rated
    -0.61
     Printed
    -0.60
    depending
    -0.59
    someone
    -0.59
    forge
    -0.58
    POSITIVE LOGITS
     counterparts
    0.88
     woes
    0.83
     counterpart
    0.78
     antics
    0.77
    mates
    0.73
     mates
    0.73
    nings
    0.73
    cles
    0.71
    ings
    0.69
     exploits
    0.67
    Activations Density 0.517%

    No Known Activations