© 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. 1-RES-JB
    11. 5185
    Prev
    Next
    INDEX
    Explanations

    mentions of different types and aspects of furniture

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of furniture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ml
    -0.77
     Ibid
    -0.68
     HIGH
    -0.67
    ttle
    -0.67
    uberty
    -0.65
    512
    -0.64
    ounty
    -0.64
    aneously
    -0.64
    sen
    -0.63
    ilitary
    -0.62
    POSITIVE LOGITS
     furniture
    1.49
    iture
    1.10
     decoration
    1.10
     decorations
    1.07
     Furn
    0.99
     chairs
    0.99
     furnish
    0.92
     Crate
    0.86
     drawer
    0.85
     carpet
    0.82
    Activations Density 0.021%

    No Known Activations