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. 21687
    Prev
    Next
    INDEX
    Explanations

    words related to computer memory sizes, specifically focusing on MB sizes ranging from 5 to 10

    oai_token-act-pair · gpt-3.5-turbo

    references to the Cosmic Microwave Background (CMB) and its associated measurements

    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
    Interstitial
    -0.64
     Gors
    -0.61
    kies
    -0.61
    ices
    -0.60
    cha
    -0.60
    coni
    -0.59
     Ori
    -0.59
    ween
    -0.59
     Comet
    -0.58
    eve
    -0.58
    POSITIVE LOGITS
    ishop
    0.89
    ounty
    0.89
    ilib
    0.89
    TeX
    0.87
    uilt
    0.85
    isoft
    0.83
    ruary
    0.81
    ular
    0.81
    uild
    0.81
    urden
    0.77
    Activations Density 0.009%

    No Known Activations