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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 3-RES-JB
    6. 19678
    Prev
    Next
    INDEX
    Explanations

    electronic devices and social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of digital devices and social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Warranty
    -0.67
     Valkyrie
    -0.63
     warranty
    -0.62
     Chrom
    -0.62
     Bethlehem
    -0.62
     Conclusion
    -0.61
     Rite
    -0.61
     Outer
    -0.60
     Cord
    -0.59
     MPG
    -0.59
    POSITIVE LOGITS
     meltdown
    0.81
    culosis
    0.80
    username
    0.78
     outage
    0.71
     postings
    0.68
    osphere
    0.68
    posts
    0.67
     screens
    0.66
    elaide
    0.66
    CHAT
    0.66
    Activations Density 0.239%

    No Known Activations