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. 21984
    Prev
    Next
    INDEX
    Explanations

    terms related to programming languages and syntax, particularly focusing on the "void" keyword

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to programming, especially operators and their functionalities

    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
    ppa
    -0.82
    grim
    -0.80
    icult
    -0.77
    idia
    -0.76
    oeuv
    -0.74
    rpm
    -0.73
    liam
    -0.73
     Hutch
    -0.72
     Milton
    -0.71
    aeda
    -0.69
    POSITIVE LOGITS
     constructor
    1.39
     initialization
    1.22
     parameter
    1.20
     callback
    1.19
     subclass
    1.18
     initialized
    1.17
     attributes
    1.17
     properties
    1.14
     tuple
    1.13
     variables
    1.13
    Activations Density 0.331%

    No Known Activations