© 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. 10-RES-JB
    11. 11628
    Prev
    Next
    INDEX
    Explanations

    acronyms related to technology, specifically around photovoltaics

    oai_token-act-pair · gpt-3.5-turbo

    references to photovoltaic (PV) technology and its associated metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogly
    -0.77
    quartered
    -0.64
    --------------------------------------------------------
    -0.63
    thritis
    -0.61
     deleg
    -0.59
     starve
    -0.59
     horizont
    -0.59
    pins
    -0.59
    ãĤ¨ãĥ«
    -0.59
    earance
    -0.58
    POSITIVE LOGITS
    ideos
    0.97
    iolet
    0.93
    irus
    0.91
    oodoo
    0.85
    ICES
    0.84
    antage
    0.84
    ascular
    0.83
    idia
    0.83
    III
    0.81
    iculture
    0.81
    Activations Density 0.122%

    No Known Activations