© 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. 3-RES-JB
    11. 550
    Prev
    Next
    INDEX
    Explanations

    words related to different sources of energy

    oai_token-act-pair · gpt-3.5-turbo

    references to various sources of energy and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aeper
    -0.79
    ellen
    -0.69
     satell
    -0.69
    ©¶æ¥µ
    -0.67
    Ħ¢
    -0.67
     Sheriff
    -0.66
     Jury
    -0.65
    paio
    -0.64
    ments
    -0.62
     Malt
    -0.61
    POSITIVE LOGITS
    source
    0.95
     source
    0.90
     sources
    0.90
    Fed
    0.88
    finding
    0.87
    lessly
    0.82
     Sources
    0.82
    ource
    0.77
    ources
    0.76
    forge
    0.76
    Activations Density 0.022%

    No Known Activations