© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 16127
    Prev
    Next
    INDEX
    Explanations

    graphic processing units (GPUs) and related technical specifications such as model names and configurations

    oai_token-act-pair · gpt-3.5-turbo

    specific models of graphics cards and relevant specifications

    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
    zynski
    -0.72
     Debor
    -0.70
    ilic
    -0.70
    reads
    -0.70
     orally
    -0.69
     bowel
    -0.69
    email
    -0.68
     abdom
    -0.67
    alter
    -0.67
    glers
    -0.66
    POSITIVE LOGITS
     GTX
    1.40
     GPUs
    1.27
     GeForce
    1.25
     Nvidia
    1.18
     GPU
    1.17
    PDATE
    1.16
     SLI
    1.16
     Quadro
    1.13
    GPU
    1.06
     Kepler
    1.02
    Activations Density 0.055%

    No Known Activations