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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 12900
    Prev
    Next
    INDEX
    Explanations

    references to file sizes, memory measurements, and technical specifications related to digital devices

    oai_token-act-pair · gpt-3.5-turbo

    mentions of megabyte (MB) sizes in the context of data or file sizes

    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
    theless
    -0.68
    uve
    -0.67
    cha
    -0.65
    zona
    -0.65
    lict
    -0.65
     spirits
    -0.63
    iders
    -0.61
     Gors
    -0.60
    uncture
    -0.60
     Atlantis
    -0.60
    POSITIVE LOGITS
    MB
    0.85
    TeX
    0.85
    TA
    0.85
    TI
    0.83
    ITS
    0.83
    ular
    0.80
    ularity
    0.80
    KB
    0.79
    BS
    0.78
    KK
    0.77
    Activations Density 0.009%

    No Known Activations