Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19710
    Prev
    Next
    INDEX
    Explanations

    textual computer code snippets.

    oai_token-act-pair · gpt-3.5-turbo

    specific formatting or syntactical structures used in programming or data implementation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abouts
    -0.82
     Reincarnated
    -0.78
    女
    -0.74
     furthe
    -0.71
     wives
    -0.70
     outwe
    -0.67
     foul
    -0.67
     seniors
    -0.67
     Saiyan
    -0.66
     photographed
    -0.66
    POSITIVE LOGITS
    Example
    1.33
    Installation
    1.07
    Usage
    1.06
    <?
    1.03
    Using
    1.02
    example
    0.99
    Examples
    0.99
     Example
    0.98
    Setup
    0.98
    Use
    0.96
    Activations Density 0.323%

    No Known Activations