© 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. 5260
    Prev
    Next
    INDEX
    Explanations

    internet-related terms, especially domains and companies

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Com," indicating a focus on commercial or company-related references

    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
     smelling
    -0.72
     mist
    -0.70
     trickle
    -0.70
     withheld
    -0.68
     planting
    -0.67
     rash
    -0.67
     keeper
    -0.67
     bail
    -0.66
     planted
    -0.65
     seal
    -0.64
    POSITIVE LOGITS
    Com
    3.94
    COM
    2.03
    com
    1.97
     Com
    1.91
    Cart
    1.32
     COM
    1.30
     com
    1.26
    comed
    1.24
    Comp
    1.20
    Org
    1.17
    Activations Density 0.005%

    No Known Activations