© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22687
    Prev
    Next
    INDEX
    Explanations

    the word "Test"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Test" 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
    monton
    -0.68
    gary
    -0.67
    iers
    -0.67
    law
    -0.66
    Els
    -0.65
    irection
    -0.64
    acan
    -0.64
    rang
    -0.63
     euros
    -0.63
    conom
    -0.62
    POSITIVE LOGITS
     Test
    3.83
     Tests
    3.07
    Test
    2.90
     test
    2.41
     TEST
    2.35
    test
    2.22
     Testing
    2.22
     tests
    2.01
    Testing
    1.86
    tests
    1.85
    Activations Density 0.009%

    No Known Activations