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. 11-RES-JB
    6. 16892
    Prev
    Next
    INDEX
    Explanations

    phrases related to characteristics of products or services, such as 'easy to use' and 'fast turnaround'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe usability and efficiency in applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pta
    -0.78
    moil
    -0.78
     Eliot
    -0.73
    ortmund
    -0.73
    orsi
    -0.72
     Struggle
    -0.71
     Unleashed
    -0.71
    acan
    -0.68
    peak
    -0.67
    phia
    -0.67
    POSITIVE LOGITS
     convenient
    1.33
     efficient
    1.32
     scalable
    1.32
     affordable
    1.32
     reliable
    1.30
     inexpensive
    1.29
     hassle
    1.24
     accessible
    1.24
     economical
    1.23
     customizable
    1.21
    Activations Density 0.202%

    No Known Activations