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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16015
    Prev
    Next
    INDEX
    Explanations

    terms related to the automotive industry

    oai_token-act-pair · gpt-3.5-turbo

    references to the automotive industry and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unin
    -0.91
    ope
    -0.88
    urat
    -0.88
    chens
    -0.87
    aido
    -0.86
    itudes
    -0.84
    opy
    -0.84
    asio
    -0.82
    opes
    -0.82
    acks
    -0.82
    POSITIVE LOGITS
     industry
    0.90
    âĹ¼
    0.83
     specialization
    0.76
     giants
    0.73
    Products
    0.72
     powerhouse
    0.71
     literature
    0.70
     Industry
    0.69
    ONSORED
    0.69
    Materials
    0.68
    Activations Density 0.049%

    No Known Activations