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. 6666
    Prev
    Next
    INDEX
    Explanations

    references to the city of Dubai

    oai_token-act-pair · gpt-3.5-turbo

    references to Dubai and the UAE

    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
    avery
    -0.78
    urgical
    -0.78
    urgy
    -0.77
    baugh
    -0.77
    fig
    -0.75
    essee
    -0.74
    ages
    -0.73
    nect
    -0.72
     Lovecraft
    -0.71
    chrom
    -0.69
    POSITIVE LOGITS
     Dhabi
    1.08
     Emir
    1.03
    querque
    0.91
     Emirates
    0.85
     Municip
    0.85
     Petroleum
    0.79
     Dubai
    0.79
     Cooperation
    0.77
    ilitation
    0.76
    Leaks
    0.75
    Activations Density 0.029%

    No Known Activations