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. 10-RES-JB
    6. 353
    Prev
    Next
    INDEX
    Explanations

    phrases related to software development tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to creating and executing plans or structures

    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
    âĢİ
    -0.68
    âĢ¢
    -0.67
     Confeder
    -0.65
    ocaust
    -0.63
    reb
    -0.63
    crit
    -0.62
    avery
    -0.62
    antz
    -0.61
    aband
    -0.60
    Correction
    -0.60
    POSITIVE LOGITS
     initialize
    1.21
     initialization
    1.01
     Lets
    1.00
     subclass
    0.93
     init
    0.91
     python
    0.90
     initialized
    0.89
     Create
    0.87
     helper
    0.87
     snippet
    0.87
    Activations Density 0.289%

    No Known Activations