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. 7-RES-JB
    6. 22031
    Prev
    Next
    INDEX
    Explanations

    references to software or technology-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to apps and technology-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    horse
    -0.73
    illac
    -0.69
    enegger
    -0.68
     Polk
    -0.68
    llan
    -0.68
    jab
    -0.66
    ku
    -0.65
    Pages
    -0.65
    wick
    -0.64
    etter
    -0.64
    POSITIVE LOGITS
    ividual
    0.84
     purchases
    0.84
     inspection
    0.82
     interaction
    0.79
     inspections
    0.79
     sales
    0.78
     interviews
    0.77
     activities
    0.77
     testing
    0.76
     interview
    0.75
    Activations Density 0.083%

    No Known Activations