© 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. 17403
    Prev
    Next
    INDEX
    Explanations

    phrases related to the organization "Moms Demand Action"

    oai_token-act-pair · gpt-3.5-turbo

    references to the group "Moms Demand Action"

    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
    âĸ¬
    -0.80
    âĸ¬âĸ¬
    -0.70
    ebook
    -0.66
    lde
    -0.66
     cu
    -0.64
     contact
    -0.62
    Ben
    -0.61
    RIC
    -0.61
     disqual
    -0.60
    consider
    -0.58
    POSITIVE LOGITS
    oms
    1.37
    ayer
    1.14
    orrow
    1.12
    chool
    1.08
    atis
    1.01
    osate
    0.97
    peed
    0.95
    ummer
    0.91
    ippi
    0.90
    atoes
    0.90
    Activations Density 0.006%

    No Known Activations