© 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. 10-RES-JB
    11. 1376
    Prev
    Next
    INDEX
    Explanations

    health-related terms and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with significant concepts, issues, or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unaffected
    -0.63
     unavailable
    -0.61
     unsupported
    -0.61
    aples
    -0.58
    avering
    -0.58
     overcoming
    -0.57
    albeit
    -0.57
     unmarked
    -0.57
     ancest
    -0.56
    ranging
    -0.56
    POSITIVE LOGITS
     entails
    1.29
     might
    0.94
     looks
    0.90
    really
    0.89
     ought
    0.88
     exists
    0.87
     entail
    0.84
     SHOULD
    0.84
     would
    0.83
     relates
    0.83
    Activations Density 0.193%

    No Known Activations