© 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. 1-RES-JB
    11. 3419
    Prev
    Next
    INDEX
    Explanations

    words related to scientists

    oai_token-act-pair · gpt-3.5-turbo

    references to scientists in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teen
    -0.74
    loaded
    -0.73
    elve
    -0.69
     Territories
    -0.69
    si
    -0.67
    ealing
    -0.67
    thening
    -0.66
    dos
    -0.64
     Pradesh
    -0.63
    onement
    -0.61
    POSITIVE LOGITS
     scientist
    1.29
     chemist
    1.10
     physicist
    1.03
     biologist
    0.99
    natureconservancy
    0.96
     Scientist
    0.94
     researcher
    0.87
     economist
    0.85
     educator
    0.83
    ãĤ¶
    0.83
    Activations Density 0.011%

    No Known Activations