© 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. 13233
    Prev
    Next
    INDEX
    Explanations

    words related to water reservoirs

    oai_token-act-pair · gpt-3.5-turbo

    references to reservoirs and water storage

    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
    Else
    -0.79
     Glory
    -0.75
     Kinnikuman
    -0.70
     Honour
    -0.69
    ihad
    -0.63
    ALK
    -0.62
    OTO
    -0.61
    rian
    -0.61
     Banner
    -0.61
    ################
    -0.61
    POSITIVE LOGITS
     reservoir
    1.48
     reservoirs
    1.40
     basin
    0.87
     Reserv
    0.80
     lake
    0.76
     glim
    0.74
    lain
    0.73
    itiz
    0.73
     fountain
    0.73
    isSpecialOrderable
    0.73
    Activations Density 0.008%

    No Known Activations