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. 10-RES-JB
    6. 24091
    Prev
    Next
    INDEX
    Explanations

    discussions about various topics related to technology, economics or finance

    oai_token-act-pair · gpt-3.5-turbo

    discussions about technology and its implications

    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
    toggle
    -0.84
    Enlarge
    -0.76
    Thousands
    -0.74
    recorded
    -0.73
     Adolf
    -0.72
     videot
    -0.72
     afterward
    -0.70
     ÂŃ
    -0.69
    famous
    -0.68
     Beverly
    -0.67
    POSITIVE LOGITS
     decentral
    1.19
     organis
    1.01
     roadmap
    0.96
     devs
    0.95
     anarchists
    0.95
     implementations
    0.94
     ICO
    0.93
     decentralized
    0.93
     systemd
    0.93
     pragmatic
    0.93
    Activations Density 1.072%

    No Known Activations