© 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. 2-RES-JB
    11. 12624
    Prev
    Next
    INDEX
    Explanations

    mentions of solar-related terms, especially "Solar Cube" and "Solar"

    oai_token-act-pair · gpt-3.5-turbo

    references to solar energy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sburgh
    -0.96
    enance
    -0.88
    hov
    -0.82
    Downloadha
    -0.82
    onse
    -0.81
    ublic
    -0.79
    ãĤĤ
    -0.79
    ITNESS
    -0.77
    raints
    -0.77
    ¿½
    -0.77
    POSITIVE LOGITS
    Solar
    0.92
     Solar
    0.81
    orbit
    0.81
     Eclipse
    0.80
    City
    0.80
    plan
    0.79
    oplan
    0.79
    beam
    0.78
     eclipse
    0.78
     Powered
    0.77
    Activations Density 0.011%

    No Known Activations