© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 17508
    Prev
    Next
    INDEX
    Explanations

    phrases related to freedom of information laws

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "freedom" and related rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doom
    -0.85
     prest
    -0.80
     veins
    -0.77
     slap
    -0.77
     sty
    -0.76
     upside
    -0.75
     sab
    -0.75
     dynam
    -0.74
     gust
    -0.73
     looting
    -0.73
    POSITIVE LOGITS
     Detail
    1.00
     Childhood
    0.95
     Information
    0.94
     Projects
    0.94
     Teachers
    0.94
    Lear
    0.93
     Computing
    0.93
     Athlet
    0.91
     Practices
    0.91
     Investments
    0.90
    Activations Density 0.074%

    No Known Activations