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. 4-RES-JB
    6. 9833
    Prev
    Next
    INDEX
    Explanations

    references to large scale infrastructure projects

    oai_token-act-pair · gpt-3.5-turbo

    mentions of infrastructure projects

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

    No Comments

    Negative Logits
    osate
    -0.87
    DOS
    -0.80
    lua
    -0.76
    ãĤ¦ãĤ¹
    -0.76
    âķIJâķIJ
    -0.69
    Ul
    -0.69
    asus
    -0.66
    BO
    -0.65
    alties
    -0.65
    bi
    -0.65
    POSITIVE LOGITS
     projects
    1.07
    afety
    0.99
     undertaken
    0.89
    uggest
    0.85
    chool
    0.83
     underway
    0.82
     Projects
    0.81
    projects
    0.81
    peak
    0.80
    etter
    0.77
    Activations Density 0.025%

    No Known Activations