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. 21015
    Prev
    Next
    INDEX
    Explanations

    words related to coding and programming, specifically around array operations and implementations

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terminology related to programming, specifically arrays and functions

    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
     Pioneer
    -0.73
     Alien
    -0.68
     Noct
    -0.66
     Tobacco
    -0.65
    gear
    -0.65
    amph
    -0.63
     Pione
    -0.63
     Dame
    -0.63
     Evening
    -0.62
     Venus
    -0.62
    POSITIVE LOGITS
    array
    1.10
     constructor
    1.07
    Iterator
    1.06
     expressions
    1.04
    Array
    1.04
     algebra
    1.04
     arithmetic
    1.01
    ()
    1.01
     arrays
    1.01
     computation
    0.99
    Activations Density 0.237%

    No Known Activations