Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7405
    Prev
    Next
    INDEX
    Explanations

    keywords related to graphics processing units (GPUs)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of GPUs and related technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obos
    -0.79
    email
    -0.78
    stic
    -0.77
    esty
    -0.75
    letter
    -0.75
    liness
    -0.73
    erville
    -0.72
    nton
    -0.71
    eker
    -0.68
    chin
    -0.68
    POSITIVE LOGITS
    PDATE
    1.50
    GPU
    1.02
     GPUs
    1.00
     GPU
    0.97
     computing
    0.90
     graphics
    0.88
     Quadro
    0.86
     compute
    0.85
     Nvidia
    0.79
    Boss
    0.76
    Activations Density 0.025%

    No Known Activations