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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 7321
    Prev
    Next
    INDEX
    Explanations

    terms related to communication and productivity applications, including email, calendars, contacts, and notifications

    oai_token-act-pair · gpt-3.5-turbo

    features and functionalities related to productivity and communication applications

    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
    aughs
    -0.82
    abama
    -0.80
    osph
    -0.78
    eln
    -0.77
    aughtered
    -0.77
    querque
    -0.76
    phal
    -0.76
    fighters
    -0.74
    amar
    -0.74
    bett
    -0.73
    POSITIVE LOGITS
     Users
    0.93
     Settings
    0.92
     Cortana
    0.90
     Desktop
    0.89
     Folder
    0.88
     Gmail
    0.88
     Extensions
    0.88
     Dropbox
    0.86
     UI
    0.86
     Server
    0.86
    Activations Density 0.254%

    No Known Activations