© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 21210
    Prev
    Next
    INDEX
    Explanations

    phrases related to photovoltaic (solar panel) technology

    oai_token-act-pair · gpt-3.5-turbo

    references to photovoltaic energy technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fix
    -0.64
    dress
    -0.64
    comb
    -0.63
     womb
    -0.63
     cane
    -0.62
     contrad
    -0.60
    ħĭ
    -0.59
    ĨĴ
    -0.59
    gest
    -0.59
    arthed
    -0.57
    POSITIVE LOGITS
    ski
    1.45
    ideo
    1.22
    irus
    1.07
    ille
    1.06
    oice
    1.01
    iew
    0.97
    ascular
    0.96
    anni
    0.92
    sky
    0.92
    ideos
    0.92
    Activations Density 0.032%

    No Known Activations