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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 519
    Prev
    Next
    INDEX
    Explanations

    the word "laboratory"

    oai_token-act-pair · gpt-4-turbo

    phrases or words related to laboratory experiments

    oai_token-act-pair · gpt-3.5-turbo

    references to laboratories or laboratory settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĦ
    -0.71
    Torrent
    -0.69
    hua
    -0.68
    speed
    -0.67
    frey
    -0.66
    Vote
    -0.65
    ternity
    -0.63
    whatever
    -0.62
    pg
    -0.62
    adding
    -0.62
    POSITIVE LOGITS
    rador
    1.21
     laboratory
    1.07
     technician
    0.93
     laboratories
    0.91
     Laboratory
    0.91
     Laboratories
    0.88
     chemist
    0.88
     labs
    0.83
    orer
    0.79
    opath
    0.78
    Activations Density 0.011%

    No Known Activations