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. 8-RES-JB
    6. 15432
    Prev
    Next
    INDEX
    Explanations

    nouns related to data storage sizes, particularly mentioning megabytes (MB)

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements of data sizes or bandwidths in megabytes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zona
    -0.73
    ources
    -0.73
    uve
    -0.72
    cha
    -0.65
    mosp
    -0.65
     Martial
    -0.62
    etheus
    -0.62
    ptive
    -0.60
     Patron
    -0.59
     Balt
    -0.59
    POSITIVE LOGITS
    TeX
    0.89
    uild
    0.84
    oru
    0.83
    ular
    0.82
    illion
    0.81
    iotic
    0.80
    arrass
    0.79
    tu
    0.79
    undo
    0.78
    TA
    0.77
    Activations Density 0.038%

    No Known Activations