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. 18665
    Prev
    Next
    INDEX
    Explanations

    indicators of strong emotions or high intensity situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    strings of characters that resemble random symbols and letters

    oai_token-act-pair · gpt-3.5-turbo
    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
     footing
    -0.67
     leaping
    -0.59
     deductions
    -0.59
     reneg
    -0.58
     run
    -0.58
     dangling
    -0.57
    restling
    -0.57
     grouping
    -0.57
     ropes
    -0.57
    lling
    -0.57
    POSITIVE LOGITS
    rawdownloadcloneembedreportprint
    0.97
    Posted
    0.94
    ccording
    0.92
    Loading
    0.91
    Emb
    0.91
    STER
    0.89
    Author
    0.88
    Reviewed
    0.87
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.85
    Product
    0.84
    Activations Density 0.129%

    No Known Activations