© 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. 11961
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'water'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of water 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
     AVG
    -0.67
     execut
    -0.66
     overt
    -0.66
     Advent
    -0.64
    ATIVE
    -0.62
     rev
    -0.62
     partName
    -0.61
     rel
    -0.60
     chromosomes
    -0.58
     Apocalypse
    -0.57
    POSITIVE LOGITS
    water
    4.36
    waters
    2.41
    Water
    2.16
    ewater
    1.80
     water
    1.76
     Water
    1.72
     waters
    1.39
    wine
    1.37
    sea
    1.21
     freshwater
    1.17
    Activations Density 0.015%

    No Known Activations