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. 8-RES-JB
    6. 5288
    Prev
    Next
    INDEX
    Explanations

    keywords related to technical instructions and projects

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to reports, projects, and initiatives in technology and community service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.80
    itably
    -0.78
     chains
    -0.71
     separatists
    -0.68
     muted
    -0.66
    etheless
    -0.66
     doubled
    -0.66
     oranges
    -0.66
     flatt
    -0.65
     quo
    -0.64
    POSITIVE LOGITS
     Advisory
    1.06
     Plan
    1.03
     Assessment
    1.01
     Partner
    1.00
     Practices
    0.98
     Skills
    0.98
     Guidelines
    0.97
     Meter
    0.97
     Account
    0.96
     Application
    0.96
    Activations Density 0.401%

    No Known Activations