© 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. 14887
    Prev
    Next
    INDEX
    Explanations

    the substring "om" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the token "om"

    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
    EngineDebug
    -0.74
     Rapids
    -0.69
     Rowe
    -0.67
     OWN
    -0.62
    è£ħ
    -0.62
     Shan
    -0.61
     cached
    -0.60
     deficit
    -0.59
     Discovery
    -0.59
     charter
    -0.59
    POSITIVE LOGITS
    om
    4.13
    OM
    2.04
    omas
    1.98
    oms
    1.93
    omic
    1.89
    ome
    1.80
    omy
    1.79
    oma
    1.77
    omed
    1.72
    omon
    1.69
    Activations Density 0.015%

    No Known Activations