© 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. 16085
    Prev
    Next
    INDEX
    Explanations

    words related to solid-state drives (SSDs), Serial ATA (SATA), and specific technology terms

    oai_token-act-pair · gpt-3.5-turbo

    references to solid-state drives (SSDs) and associated technical specifications

    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
    xon
    -0.87
    ois
    -0.77
    yip
    -0.73
    nel
    -0.68
     Islamic
    -0.67
    bidden
    -0.66
     UNESCO
    -0.66
    govtrack
    -0.65
    enegger
    -0.65
    ãĤ±
    -0.64
    POSITIVE LOGITS
     storage
    1.03
     SSD
    1.00
     HDD
    0.89
     accelerator
    0.88
     Storage
    0.81
    DAQ
    0.79
     capacities
    0.78
     capacitor
    0.77
    Ds
    0.76
    MC
    0.74
    Activations Density 0.008%

    No Known Activations