© 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. 6-RES-JB
    11. 17753
    Prev
    Next
    INDEX
    Explanations

    references to furniture, specifically chairs

    oai_token-act-pair · gpt-3.5-turbo

    references to chairs and seating arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Territories
    -0.79
    aries
    -0.75
    arily
    -0.72
    actionDate
    -0.69
    DN
    -0.65
    onductor
    -0.64
    ï¸ı
    -0.62
    oil
    -0.62
    ocy
    -0.62
     Rounds
    -0.62
    POSITIVE LOGITS
    lift
    1.24
    chair
    0.94
     furniture
    0.94
     chairs
    0.91
    holder
    0.90
    tops
    0.89
    chairs
    0.88
     chair
    0.87
     recl
    0.86
     cush
    0.85
    Activations Density 0.032%

    No Known Activations