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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 5621
    Prev
    Next
    INDEX
    Explanations

    mentions of specific graphics cards and computer processors

    oai_token-act-pair · gpt-3.5-turbo

    references to AMD products, specifically graphics cards and processors

    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
    glers
    -0.78
    chin
    -0.76
    cott
    -0.76
     sugg
    -0.71
    HF
    -0.71
    under
    -0.70
    ffer
    -0.70
    othe
    -0.69
    ski
    -0.68
    lem
    -0.68
    POSITIVE LOGITS
     RX
    1.01
     Radeon
    0.90
     GPUs
    0.89
    adeon
    0.88
     Graphics
    0.82
    ificial
    0.81
     GPU
    0.81
     Adren
    0.77
     graphics
    0.77
    GPU
    0.76
    Activations Density 0.012%

    No Known Activations