© 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. 8-RES-JB
    11. 7777
    Prev
    Next
    INDEX
    Explanations

    words related to chemistry, particularly minerals and elements

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "min" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    renheit
    -0.70
    master
    -0.68
     Poles
    -0.66
    ripp
    -0.63
    catentry
    -0.63
    kok
    -0.62
    masters
    -0.62
    nesday
    -0.60
    riter
    -0.60
    lings
    -0.59
    POSITIVE LOGITS
    nesota
    1.21
    utes
    1.15
    ister
    1.06
    otaur
    1.00
    ority
    0.97
    ISTER
    0.94
    isters
    0.90
    neapolis
    0.87
    istration
    0.86
    eral
    0.83
    Activations Density 0.032%

    No Known Activations