© 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. 4-RES-JB
    11. 17168
    Prev
    Next
    INDEX
    Explanations

    terms related to dental care and health

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dental health and associations

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

    No Comments

    Negative Logits
    alions
    -0.85
    advertisement
    -0.84
    sheet
    -0.78
    ============
    -0.72
    enegger
    -0.72
    wikipedia
    -0.72
    inelli
    -0.72
    ========
    -0.71
    accept
    -0.71
    agy
    -0.69
    POSITIVE LOGITS
     hygiene
    0.80
     assistants
    0.73
     dental
    0.72
    cium
    0.70
     faculties
    0.69
     fungus
    0.68
     handic
    0.68
     palate
    0.68
     assistant
    0.67
     reservation
    0.66
    Activations Density 0.007%

    No Known Activations