© 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. 10-RES-JB
    11. 3040
    Prev
    Next
    INDEX
    Explanations

    words related to testing and examination

    oai_token-act-pair · gpt-3.5-turbo

    references to testing and experimental processes

    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
     Klux
    -0.83
    é»Ĵ
    -0.75
    wikipedia
    -0.75
    conom
    -0.74
    ocial
    -0.73
    Els
    -0.72
    orthern
    -0.71
    cloth
    -0.71
    ¬¼
    -0.71
     mortg
    -0.70
    POSITIVE LOGITS
     tests
    2.04
     testing
    1.92
     test
    1.91
     Testing
    1.82
     Tests
    1.80
    Testing
    1.74
     testers
    1.73
    tests
    1.64
     tested
    1.61
     TEST
    1.58
    Activations Density 0.473%

    No Known Activations