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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 1131
    Prev
    Next
    INDEX
    Explanations

    words related to printing or sharing content through different platforms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Print" in various contexts

    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
    onite
    -0.79
    ority
    -0.69
    venants
    -0.68
     Oaks
    -0.67
    usher
    -0.67
    xual
    -0.66
    opoulos
    -0.66
    hov
    -0.65
     Witnesses
    -0.64
    arios
    -0.64
    POSITIVE LOGITS
    Print
    1.06
     Print
    1.03
    Writer
    0.84
    sheet
    0.79
    ername
    0.78
    Screen
    0.74
    cies
    0.74
    ln
    0.71
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.69
     prints
    0.68
    Activations Density 0.012%

    No Known Activations