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. 16700
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming language and software development

    oai_token-act-pair · gpt-3.5-turbo

    terms related to programming languages and their features

    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
    76561
    -0.78
    aukee
    -0.77
    borough
    -0.77
    olit
    -0.73
     Hollow
    -0.71
    cial
    -0.69
    ricular
    -0.68
    liction
    -0.67
    hower
    -0.67
     graves
    -0.67
    POSITIVE LOGITS
     implementations
    1.18
     extensions
    1.04
     APIs
    0.97
     plugins
    0.96
     runtime
    0.93
     optimizations
    0.92
     implementation
    0.92
     SDK
    0.91
     software
    0.89
     interfaces
    0.89
    Activations Density 0.146%

    No Known Activations