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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 18994
    Prev
    Next
    INDEX
    Explanations

    proper nouns or technical terms related to a specific entity or product called "Vega", "Ryzen 2", and "Mant2."

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to specific brands and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oho
    -0.87
    nesses
    -0.86
    gling
    -0.80
    bling
    -0.80
    glers
    -0.80
    kson
    -0.79
    ocene
    -0.78
    bler
    -0.75
    pite
    -0.75
    ocrine
    -0.75
    POSITIVE LOGITS
     Vega
    1.66
     Squadron
    1.09
     Polaris
    1.01
     GPUs
    0.88
     RX
    0.79
     Sector
    0.77
     Lug
    0.71
     Vendor
    0.70
     Valkyrie
    0.70
     HDL
    0.69
    Activations Density 0.026%

    No Known Activations