© 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. 3888
    Prev
    Next
    INDEX
    Explanations

    references to different types of water, such as drinking water, bottled water, and even rainwater

    oai_token-act-pair · gpt-3.5-turbo

    references to bottled water and related topics

    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
     Waves
    -0.75
     Spac
    -0.69
     Planes
    -0.67
     Maritime
    -0.67
     Neural
    -0.63
     flights
    -0.62
     Wide
    -0.61
     positional
    -0.61
     Aircraft
    -0.61
     Regions
    -0.61
    POSITIVE LOGITS
    anasia
    0.96
    liga
    0.85
    arette
    0.82
    ertodd
    0.81
    acco
    0.80
    potion
    0.76
    paste
    0.76
    akery
    0.74
    chery
    0.74
    washer
    0.73
    Activations Density 0.356%

    No Known Activations