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. 2-RES-JB
    6. 18171
    Prev
    Next
    INDEX
    Explanations

    keywords related to data storage and disk management

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of storage devices, particularly disks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndum
    -0.82
    pheus
    -0.77
    adesh
    -0.72
     Aval
    -0.71
    kok
    -0.71
    uyomi
    -0.68
    ean
    -0.67
     Bee
    -0.67
    ourgeois
    -0.66
    yip
    -0.66
    POSITIVE LOGITS
    Disk
    1.14
     disks
    1.13
     disk
    1.07
    disk
    1.03
    ussion
    0.91
     Disk
    0.91
    ettes
    0.84
    ette
    0.79
     shelves
    0.77
    label
    0.77
    Activations Density 0.004%

    No Known Activations