© 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. 0-RES-JB
    11. 10346
    Prev
    Next
    INDEX
    Explanations

    references to the software MongoDB

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ongo" and related words or phrases associated with ongoing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sutherland
    -0.74
     Nir
    -0.74
     laureate
    -0.73
     awoken
    -0.69
     Haf
    -0.69
     Spectre
    -0.68
     Vive
    -0.67
     Lawn
    -0.66
     cov
    -0.65
     Thorn
    -0.64
    POSITIVE LOGITS
    ongo
    2.70
    oco
    2.47
    enda
    1.62
    imo
    1.59
    endo
    1.59
    undo
    1.55
    udo
    1.50
    into
    1.48
    ento
    1.44
    eco
    1.40
    Activations Density 0.024%

    No Known Activations