© 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. 4-RES-JB
    11. 7021
    Prev
    Next
    INDEX
    Explanations

    furniture-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to furniture and associated items

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

    No Comments

    Negative Logits
    awar
    -0.67
    ilitary
    -0.66
    olics
    -0.63
     Ibid
    -0.62
     Violent
    -0.61
    mary
    -0.61
    aneously
    -0.60
     CNS
    -0.60
    20439
    -0.60
     retribution
    -0.60
    POSITIVE LOGITS
     furniture
    1.22
     decoration
    0.96
     drawer
    0.91
    iture
    0.90
     decorations
    0.87
     chairs
    0.80
     shelves
    0.80
     arrang
    0.78
    pillar
    0.76
     Furn
    0.75
    Activations Density 0.016%

    No Known Activations