Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 15319
    Prev
    Next
    INDEX
    Explanations

    phrases related to power generation and energy sources

    oai_token-act-pair · gpt-3.5-turbo

    references to electricity generation and sources of power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    romeda
    -0.77
    eryl
    -0.75
     Von
    -0.73
    ead
    -0.71
     Bei
    -0.71
    erella
    -0.69
    yll
    -0.69
    eret
    -0.69
    yip
    -0.68
    ean
    -0.68
    POSITIVE LOGITS
    houses
    1.19
     outage
    0.98
     generators
    0.98
     stations
    0.96
    station
    0.93
     plants
    0.90
    boats
    0.85
     grids
    0.85
     consumption
    0.85
    plant
    0.85
    Activations Density 0.035%

    No Known Activations