© 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. 2-RES-JB
    11. 17252
    Prev
    Next
    INDEX
    Explanations

    references to a database management system called MongoDB

    oai_token-act-pair · gpt-3.5-turbo

    the term "mong" and its variations, indicating a focus on something related to that term or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Skydragon
    -0.78
     attm
    -0.74
     Independence
    -0.71
     FORM
    -0.69
     Sector
    -0.68
     Leilan
    -0.68
    perture
    -0.67
    Merit
    -0.66
    phabet
    -0.66
    istine
    -0.65
    POSITIVE LOGITS
    mong
    1.33
    atown
    1.04
    ument
    0.86
    eful
    0.83
    olin
    0.81
    rers
    0.80
    rer
    0.80
    ²¾
    0.79
    efully
    0.79
    ong
    0.78
    Activations Density 0.014%

    No Known Activations