© 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. 7-RES-JB
    11. 22973
    Prev
    Next
    INDEX
    Explanations

    words related to nuclear topics

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to nuclear energy and radiation

    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
     Mara
    -0.70
     Ribbon
    -0.70
     Goo
    -0.69
     Kend
    -0.65
     Kik
    -0.65
     Aires
    -0.63
     Rune
    -0.60
     Melody
    -0.59
     DevOnline
    -0.59
     denomin
    -0.59
    POSITIVE LOGITS
    /)
    1.26
    _
    1.18
    _-_
    1.14
    _(
    0.99
    __
    0.97
    ulhu
    0.92
    /#
    0.91
    arthed
    0.91
    "},"
    0.90
    />
    0.88
    Activations Density 0.092%

    No Known Activations