© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 15725
    Prev
    Next
    INDEX
    Explanations

    references to outdoor spaces, particularly focusing on lawn-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to lawns and landscaping

    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
    ========
    -0.73
    ICT
    -0.69
    Published
    -0.67
    ictions
    -0.67
    Lear
    -0.66
    oice
    -0.66
    ============
    -0.66
    icts
    -0.63
    Reviewed
    -0.62
    esthetic
    -0.61
    POSITIVE LOGITS
     lawn
    1.04
    iage
    1.03
    shire
    1.02
    enium
    0.96
     Lawn
    0.89
    stones
    0.86
    chair
    0.85
    conservancy
    0.85
     patio
    0.84
    weed
    0.83
    Activations Density 0.010%

    No Known Activations