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. 10901
    Prev
    Next
    INDEX
    Explanations

    email service providers, with a strong preference for Gmail

    oai_token-act-pair · gpt-3.5-turbo

    references to email services and storage solutions

    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
    nings
    -0.83
    semble
    -0.80
    ~~~~~~~~~~~~~~~~
    -0.72
    ivism
    -0.71
    hani
    -0.71
    lass
    -0.71
    âķIJâķIJ
    -0.71
    ————————————————
    -0.71
    66666666
    -0.68
    kef
    -0.67
    POSITIVE LOGITS
     Gmail
    1.09
     inbox
    1.01
    awei
    0.78
     Launcher
    0.74
     Dropbox
    0.73
    Connection
    0.73
     Analytics
    0.73
     Keyboard
    0.72
     Pavilion
    0.72
     subscribers
    0.71
    Activations Density 0.014%

    No Known Activations