© 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. 0-RES-JB
    11. 20145
    Prev
    Next
    INDEX
    Explanations

    terms related to testing or examination

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of testing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iture
    -0.70
    lesiastical
    -0.69
    itement
    -0.68
    adia
    -0.64
    orship
    -0.62
    atism
    -0.60
    retion
    -0.59
    ques
    -0.59
    ibrary
    -0.58
    ordinate
    -0.58
    POSITIVE LOGITS
     tested
    3.85
    tested
    2.57
     tests
    2.03
     test
    2.03
     testing
    2.02
    Testing
    1.87
     Tests
    1.87
     Testing
    1.85
     testers
    1.79
    testing
    1.75
    Activations Density 0.013%

    No Known Activations