© 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. 840
    Prev
    Next
    INDEX
    Explanations

    information related to laboratory experiments involving mice

    oai_token-act-pair · gpt-3.5-turbo

    references to mice in scientific studies

    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
    soDeliveryDate
    -0.84
    ãĤ¢ãĥ«
    -0.81
    tainment
    -0.80
    rency
    -0.79
    ãĤ¦
    -0.78
    href
    -0.74
    haul
    -0.71
    jri
    -0.69
    Commission
    -0.68
    teness
    -0.68
    POSITIVE LOGITS
     mitochond
    1.09
     embryos
    1.08
     genetically
    1.06
     immune
    0.99
     genome
    0.98
     mice
    0.96
     brains
    0.96
     vaccinated
    0.96
     cultured
    0.96
     mitochondrial
    0.95
    Activations Density 0.123%

    No Known Activations