© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 23399
    Prev
    Next
    INDEX
    Explanations

    words related to ancient or outdated things

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of antiquity and its related terms

    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
    LOD
    -0.85
    Assembly
    -0.82
    Delivery
    -0.76
    Contact
    -0.71
    âķIJâķIJ
    -0.71
    Conclusion
    -0.68
    feed
    -0.67
    âķIJ
    -0.67
    Examples
    -0.66
    Charge
    -0.66
    POSITIVE LOGITS
     antiqu
    1.15
    itized
    0.88
    ictionary
    0.87
     Antiqu
    0.87
    itiz
    0.86
    iencies
    0.85
    ifax
    0.83
    ated
    0.83
    iqueness
    0.83
    ities
    0.82
    Activations Density 0.011%

    No Known Activations