© 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. 7634
    Prev
    Next
    INDEX
    Explanations

    words related to furniture, specifically tables

    oai_token-act-pair · gpt-3.5-turbo

    references to tables in various contexts

    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
    angan
    -0.75
    aine
    -0.67
    gan
    -0.66
    iasm
    -0.65
    igma
    -0.64
    âĹ¼
    -0.63
    fre
    -0.62
    CB
    -0.58
    phas
    -0.58
    ong
    -0.57
    POSITIVE LOGITS
     tables
    4.18
     Tables
    2.67
     table
    2.57
     Table
    1.82
    table
    1.79
     desks
    1.76
    Table
    1.63
     TABLE
    1.59
     benches
    1.49
     chairs
    1.42
    Activations Density 0.011%

    No Known Activations