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. 10-RES-JB
    6. 2358
    Prev
    Next
    INDEX
    Explanations

    phrases starting with the indefinite article "a" followed by a noun

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the article "a."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    intent
    -0.73
    lest
    -0.72
    eston
    -0.71
     onwards
    -0.70
    seekers
    -0.70
    fights
    -0.70
    boats
    -0.70
    Edit
    -0.68
    Arizona
    -0.67
    pages
    -0.66
    POSITIVE LOGITS
     tad
    1.10
     reflection
    1.06
     testament
    1.05
     remnant
    1.03
     mixture
    1.03
     coincidence
    1.01
     result
    1.00
     parody
    0.99
     placeholder
    0.98
     culmination
    0.98
    Activations Density 0.266%

    No Known Activations