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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 4545
    Prev
    Next
    INDEX
    Explanations

    code snippets related to programming languages in a static context

    oai_token-act-pair · gpt-3.5-turbo

    programming keywords and concepts related to object-oriented programming

    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
    grain
    -0.87
    aea
    -0.85
    ocene
    -0.84
    orsi
    -0.77
    Magikarp
    -0.77
    aston
    -0.77
    ange
    -0.74
    76561
    -0.73
    telling
    -0.72
    won
    -0.72
    POSITIVE LOGITS
     fn
    0.88
     enum
    0.87
     Array
    0.82
     __
    0.79
     bool
    0.78
     func
    0.75
     std
    0.74
     static
    0.72
     vec
    0.69
     Uri
    0.68
    Activations Density 0.042%

    No Known Activations