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. 1-RES-JB
    6. 11817
    Prev
    Next
    INDEX
    Explanations

    phrases related to downloading digital content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "download."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perty
    -0.81
     Herm
    -0.72
    ofi
    -0.67
    essen
    -0.66
    uchin
    -0.65
     intest
    -0.65
    aults
    -0.64
     eyed
    -0.62
    bara
    -0.62
     dilig
    -0.62
    POSITIVE LOGITS
     downloads
    1.34
     download
    1.26
     Download
    1.25
     Downloads
    1.05
     downloading
    1.05
     downloaded
    0.98
    LOAD
    0.96
    download
    0.93
    Download
    0.90
    DragonMagazine
    0.89
    Activations Density 0.008%

    No Known Activations