© 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. 11-RES-JB
    11. 20608
    Prev
    Next
    INDEX
    Explanations

    medical conditions and research findings related to various diseases

    oai_token-act-pair · gpt-3.5-turbo

    references to past occurrences or documented conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     haste
    -0.76
    inventoryQuantity
    -0.74
    externalActionCode
    -0.68
     Choice
    -0.66
    RAW
    -0.65
     Dollars
    -0.65
     Refresh
    -0.64
     Angry
    -0.64
     Appropriations
    -0.63
    Cooldown
    -0.62
    POSITIVE LOGITS
     detected
    1.78
     observed
    1.71
     reported
    1.40
     spotted
    1.39
     recorded
    1.39
     discovered
    1.38
     encountered
    1.38
     noticed
    1.36
     seen
    1.36
     noted
    1.34
    Activations Density 0.209%

    No Known Activations