© 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. 6-RES-JB
    11. 15195
    Prev
    Next
    INDEX
    Explanations

    religious terms and constitutional amendments

    oai_token-act-pair · gpt-3.5-turbo

    references to laws and constitutional amendments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hem
    -0.74
    ensis
    -0.72
    lease
    -0.69
    cli
    -0.67
    aciously
    -0.67
     thor
    -0.67
     toget
    -0.66
     deduct
    -0.65
     seniors
    -0.65
     fluoride
    -0.63
    POSITIVE LOGITS
     Majesty
    1.00
     Izan
    0.83
     Uniform
    0.81
     Honour
    0.80
    Tube
    0.80
     Matter
    0.80
    Zero
    0.80
     Country
    0.79
     Subtle
    0.78
    Va
    0.78
    Activations Density 0.977%

    No Known Activations