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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 9343
    Prev
    Next
    INDEX
    Explanations

    phrases related to information and technology

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terminology related to information and communication technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptoms
    -0.77
    zzy
    -0.71
     Soda
    -0.71
    aska
    -0.70
     Strange
    -0.70
     Bram
    -0.69
    comed
    -0.69
     Bed
    -0.67
     Aven
    -0.66
     Pearce
    -0.66
    POSITIVE LOGITS
     dissemination
    1.03
    technology
    1.00
     warfare
    1.00
     Sharing
    0.98
     sharing
    0.96
     retention
    0.96
     SHAR
    0.94
     privacy
    0.89
     technology
    0.88
     encryption
    0.88
    Activations Density 0.086%

    No Known Activations