© 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. 7133
    Prev
    Next
    INDEX
    Explanations

    terms related to biological and medical sciences, with a focus on bacteria and proteins

    oai_token-act-pair · gpt-3.5-turbo

    references to biological substances and processes

    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
    女
    -0.88
    ilitary
    -0.79
    Ire
    -0.79
    wered
    -0.73
    ptoms
    -0.73
    arity
    -0.72
    76561
    -0.71
    inventoryQuantity
    -0.70
    ļéĨĴ
    -0.69
    iminary
    -0.68
    POSITIVE LOGITS
    âĢIJ
    0.78
     morphology
    0.77
     phenotype
    0.76
     graphene
    0.74
     origin
    0.72
     genomic
    0.71
     genomes
    0.71
     nucle
    0.70
     embodiments
    0.68
     contexts
    0.67
    Activations Density 0.483%

    No Known Activations