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. 19476
    Prev
    Next
    INDEX
    Explanations

    the symbol "ĩ" occurring in various contexts within the text

    oai_token-act-pair · gpt-3.5-turbo

    a specific character or symbol, likely representing a particular type of notation or code

    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
    ters
    -0.80
    rette
    -0.76
    faced
    -0.76
    undai
    -0.76
     kernels
    -0.75
    fet
    -0.74
     bidder
    -0.72
    verts
    -0.69
     bluff
    -0.68
     stag
    -0.68
    POSITIVE LOGITS
    ا
    0.99
    ãģĨ
    0.91
    Į
    0.91
    ÑĮ
    0.89
    ĥ
    0.88
    е
    0.88
    ĩ
    0.87
    å®
    0.86
    н
    0.86
    į
    0.85
    Activations Density 0.012%

    No Known Activations