© 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. 15804
    Prev
    Next
    INDEX
    Explanations

    words related to testing or assessment

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "test" and related terms

    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
     chains
    -0.71
     opportun
    -0.66
     narc
    -0.63
     sl
    -0.63
     footing
    -0.62
     ground
    -0.60
     Brook
    -0.59
     bos
    -0.59
     Lob
    -0.58
     jugg
    -0.58
    POSITIVE LOGITS
    test
    4.01
    testing
    3.13
    testers
    3.01
    tests
    2.88
    tested
    2.26
    Test
    2.22
    tes
    1.73
     testers
    1.65
     Test
    1.63
     TEST
    1.53
    Activations Density 0.013%

    No Known Activations